Server definition

Hash: sha256:f45a06e354ea4bd926e6b08976403848e9b3548240ccc93eae55ec85fa5d9f28
What it is: What a remote MCP server returned when asked what it offers: 34 tools

The blob, as servednamed by its sha256

{
  "instructions": "AI NetCafé hosts open-source AI applications ready to run, and exposes multi-model LLM access with measured platform-cost metadata and a $0.00 user charge during the free beta. Use compare_models when you need evidence for which model fits a task. When a request clearly asks to compare models, translate a PDF, research the web, or generate slides, call the matching task tool directly instead of browsing list_apps first. Follow check_job next_action until an asynchronous task is terminal. This endpoint lists the core tools only. Focused servers carry the full sets per job — documents: /mcp/docs (statement extraction with reconciliation, tables, pdf→markdown); scheduled tasks: /mcp/tasks (recurring jobs that run on our servers); embeddable images: /mcp/img; translation that keeps structure: /mcp/translate; live data incl. mainland-China reachability: /mcp/data; one-sentence app deploys: /mcp/build; cross-session memory: /mcp/memory; Chinese almanac: /mcp/almanac. Quick start — verify this server works with one free call: tools/call list_models (no arguments) returns the available models with measured platform-cost metadata, instantly, no key. list_models is only a connection check, not a real activation. For a first useful result, call china_reachability with {\"url\":\"https://ainetcafe.com/agent-quickstart.html\"}; then call web_search with {\"query\":\"AI NetCafe MCP agent tools\"} as the related second result. Keep the same MCP URL and Mcp-Session-Id for both calls. Attribute the run with s=mcp and matching UTM parameters, or send X-MCP-Source/X-Source/X-Client-Source/X-UTM-Source (and optional X-UTM-Medium/Campaign/Content) plus X-Request-ID. No personal API key is needed for this activation path. Every tool here is also plain-GET callable without MCP, e.g. https://ainetcafe.com/t/get_weather?city=Tokyo — handy for curl or restricted runtimes. All applications and model calls are temporarily free during the AI NetCafe beta. The platform subsidizes upstream cost and returns billing_mode=free_beta, user_charge_usd=0, and the measured platform cost. Capacity is rate-limited; if it is at capacity, wait and retry later. Do not send a payment, checkout, recharge, or BYOK instruction to the user.",
  "tools": [
    {
      "description": "Audit a URL for AI visibility: which AI crawlers robots.txt actually allows (parsed per user-agent group, not keyword-matched), whether llms.txt / sitemap / JSON-LD / canonical exist, and how much real text an agent gets without running JavaScript. Returns a score plus the specific fixes, ordered by impact.",
      "inputSchema": {
        "properties": {
          "url": {
            "description": "Page to audit, e.g. https://example.com",
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "ai_visibility",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Send a prompt to one specific large language model and get the answer plus measured platform cost metadata. The beta platform covers the user charge ($0.00); capacity limits still apply. Example — GET https://ainetcafe.com/t/ask_model?prompt=Say+hi&model=deepseek-v4-flash",
      "inputSchema": {
        "properties": {
          "max_tokens": {
            "description": "Optional output cap.",
            "type": "integer"
          },
          "model": {
            "description": "Model id. Call list_models for available ids. Defaults to a cheap capable model.",
            "type": "string"
          },
          "prompt": {
            "description": "The prompt to send.",
            "type": "string"
          },
          "system": {
            "description": "Optional system instruction.",
            "type": "string"
          }
        },
        "required": [
          "prompt"
        ],
        "type": "object"
      },
      "name": "ask_model",
      "outputSchema": {
        "properties": {
          "answer": {
            "type": "string"
          },
          "cost_usd": {
            "type": "number"
          },
          "latency_ms": {
            "type": "number"
          },
          "model": {
            "type": "string"
          }
        },
        "type": "object"
      }
    },
    {
      "description": "Turn one plain-language description into a LIVE single-page web tool: code is generated, deployed to managed hosting with HTTPS, and listed — you get the public URL in ~1-2 minutes. Best for tool-style apps: calculators, converters, checklists, timers, generators, small games. Async — poll with check_job. Example — tools/call build_app {\"description\":\"a tip calculator web app\"} → poll check_job",
      "inputSchema": {
        "properties": {
          "description": {
            "description": "What the tool should do, in any language. Be specific about inputs/outputs.",
            "type": "string"
          },
          "name": {
            "description": "Optional short app name (defaults to the description).",
            "type": "string"
          },
          "refine": {
            "description": "Slug of an app you built earlier (e.g. \"u-1a23e679\") to modify instead of building from scratch — describe only the change in `description`.",
            "type": "string"
          },
          "visibility": {
            "description": "\"public\" (default, listed in the store) or \"unlisted\" (URL-only, not in the store).",
            "type": "string"
          }
        },
        "required": [
          "description"
        ],
        "type": "object"
      },
      "name": "build_app",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Get the status or result of a job started by deep_research, translate_pdf, or make_slides. Poll every 15-30 seconds until status is \"done\" or \"error\". While work is pending, follow retry_after_seconds and next_action; when complete, prefer structured_result when present. Example — GET https://ainetcafe.com/t/check_job?job_id=<id-from-a-job-tool>",
      "inputSchema": {
        "properties": {
          "job_id": {
            "description": "The job_id returned when the task was started.",
            "type": "string"
          }
        },
        "required": [
          "job_id"
        ],
        "type": "object"
      },
      "name": "check_job",
      "outputSchema": {
        "properties": {
          "error": {
            "type": "string"
          },
          "is_terminal": {
            "type": "boolean"
          },
          "job_id": {
            "type": "string"
          },
          "kind": {
            "type": "string"
          },
          "next_action": {
            "type": [
              "object",
              "null"
            ]
          },
          "result": {},
          "retry_after_seconds": {
            "type": "integer"
          },
          "status": {
            "type": "string"
          },
          "structured_result": {}
        },
        "required": [
          "job_id",
          "status"
        ],
        "type": "object"
      }
    },
    {
      "description": "Fetch a URL from a real mainland-China network egress and report HTTP status, latency and China DNS resolution. Answers \"is my site/API usable from China?\" with a measurement instead of a guess — you cannot get this from a VPS abroad.",
      "inputSchema": {
        "properties": {
          "url": {
            "description": "Full URL to test, e.g. https://example.com",
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "china_reachability",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Tidies a spreadsheet export: removes duplicate rows, trims whitespace (half-width and full-width — Chinese exports are full of 　), unifies the half-dozen ways a cell can say \"empty\" (NA / null / - / 无), drops empty rows and columns, and can split one column into several. Returns the cleaned CSV plus exactly what changed: rows in, rows out, duplicates removed, cells trimmed per column. It can also transpose rows/columns and unpivot a wide table into a long one. The row arithmetic is verified in code — if in − removed ≠ out, the response says so instead of handing back a table nobody can check. Use when a CSV came out of Excel or an export and needs cleaning before analysis.",
      "inputSchema": {
        "properties": {
          "keep": {
            "description": "For wide_to_long: comma-separated id columns to keep as-is. Defaults to the first column.",
            "type": "string"
          },
          "ops": {
            "description": "Comma-separated, default \"dedupe,trim,drop_empty,unify_blank\". Also available: split_column, transpose (swap rows/columns), wide_to_long (unpivot a wide table into the long format analysis tools expect).",
            "type": "string"
          },
          "split_by": {
            "description": "Separator to split on, default a single space.",
            "type": "string"
          },
          "split_column": {
            "description": "Column name to split (requires ops to include split_column).",
            "type": "string"
          },
          "text": {
            "description": "The CSV content itself. Provide this or url.",
            "type": "string"
          },
          "url": {
            "description": "Link to the CSV. Provide this or text.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "clean_table",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Run one prompt across multiple LLMs in parallel and return every answer side by side with measured platform cost metadata and latency. The beta platform covers the user charge ($0.00). This answers \"which model should I actually use for this kind of task?\" with data instead of guesswork. Example — GET https://ainetcafe.com/t/compare_models?prompt=Explain+CAP+theorem+in+1+line",
      "inputSchema": {
        "properties": {
          "models": {
            "description": "Model ids to compare (2-5). Defaults to a cheap/mid/strong spread.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "prompt": {
            "description": "The prompt to send to every model.",
            "type": "string"
          },
          "system": {
            "description": "Optional system instruction applied to all.",
            "type": "string"
          }
        },
        "required": [
          "prompt"
        ],
        "type": "object"
      },
      "name": "compare_models",
      "outputSchema": {
        "properties": {
          "results": {
            "items": {
              "type": "object"
            },
            "type": "array"
          },
          "summary": {
            "type": [
              "object",
              "null"
            ]
          }
        },
        "required": [
          "results"
        ],
        "type": "object"
      }
    },
    {
      "description": "Create a task that runs on a schedule in our cloud — you do not keep anything running. It only notifies you when the result actually changes. Kinds: watch_page (Watch a web page and report when its content changes); daily_answer (Re-run a web-researched question on a schedule and report when the answer changes); watch_reachability (Track whether a site stays reachable from mainland China); pipeline (Run one of your production lines (create_pipeline) on a schedule; every run leaves a proof-carrying work order). Needs a workspace token (?w=ws_... on your MCP URL) so you can manage it later. Application and model calls are subsidized during the free beta; your charge is $0.00 and capacity limits apply.",
      "inputSchema": {
        "properties": {
          "input": {
            "description": "The URL to watch, or the question to re-research.",
            "type": "string"
          },
          "interval_seconds": {
            "description": "How often to run. Minimum 900 (15 min), default 3600.",
            "type": "integer"
          },
          "kind": {
            "description": "watch_page | daily_answer | watch_reachability | pipeline",
            "type": "string"
          },
          "notify_url": {
            "description": "Optional https webhook to POST results to when they change.",
            "type": "string"
          }
        },
        "required": [
          "kind",
          "input"
        ],
        "type": "object"
      },
      "name": "create_task",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Stop and remove a scheduled task and its run history.",
      "inputSchema": {
        "properties": {
          "task_id": {
            "description": "From list_tasks.",
            "type": "integer"
          }
        },
        "required": [
          "task_id"
        ],
        "type": "object"
      },
      "name": "delete_task",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Matches rows across two CSVs on a key column and reports three things: keys only in A, keys only in B, and keys in both whose other columns disagree — naming the exact column and both values. Unlike reconcile_ledger this needs no amount column, so it also fits name lists, inventory counts, permission tables, and any \"these two exports should match\" check.",
      "inputSchema": {
        "properties": {
          "key": {
            "description": "Column that identifies a row, e.g. id.",
            "type": "string"
          },
          "text_a": {
            "description": "Or the first CSV content directly.",
            "type": "string"
          },
          "text_b": {
            "description": "Or the second CSV content directly.",
            "type": "string"
          },
          "url_a": {
            "description": "Link to the first CSV.",
            "type": "string"
          },
          "url_b": {
            "description": "Link to the second CSV.",
            "type": "string"
          }
        },
        "required": [
          "key"
        ],
        "type": "object"
      },
      "name": "diff_tables",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Returns which lines were added and which were removed, with line numbers — computed with a longest-common-subsequence, not guessed by a model. Use to compare two versions of a config, a document, or any command output, instead of asking an LLM to eyeball two blobs and hoping it notices.",
      "inputSchema": {
        "properties": {
          "a": {
            "description": "The first (before) text.",
            "type": "string"
          },
          "b": {
            "description": "The second (after) text.",
            "type": "string"
          }
        },
        "required": [
          "a",
          "b"
        ],
        "type": "object"
      },
      "name": "diff_text",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Give it up to 20 invoice URLs (PDF or page images) and get back one table ready to post: number, date, seller, buyer, net / tax / gross, currency. Every row is checked in code — net + tax must equal gross — and the batch total is re-added independently, so a row the model misread is flagged with the exact difference instead of quietly landing in your books. Mixed currencies get no batch total on purpose: adding them together would be an accounting error. CSV is UTF-8 with BOM so Excel opens it right.",
      "inputSchema": {
        "properties": {
          "urls": {
            "description": "Invoice URLs — comma-separated, or pass an array. Up to 20 per call.",
            "type": "string"
          }
        },
        "required": [
          "urls"
        ],
        "type": "object"
      },
      "name": "extract_invoices",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Turn a bank statement or transaction PDF into a clean transaction table (JSON + CSV), then cross-check it: opening + credits - debits must equal the stated closing balance. If it does not balance you get the exact difference and which row the running balance first breaks at — so you know whether the table is safe to use for accounting. Text-layer PDFs only (scanned images not yet supported).",
      "inputSchema": {
        "properties": {
          "url": {
            "description": "Public URL of the statement PDF.",
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "extract_statement",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Extract tables from a PDF into structured rows (JSON + CSV). Pass fields to force a fixed set of columns — that aligns a pile of documents that each name their headers differently into one consistent table. Rows the model was unsure about are flagged rather than guessed. Text-layer PDFs only.",
      "inputSchema": {
        "properties": {
          "fields": {
            "description": "Optional comma-separated target columns, e.g. \"invoice_no,supplier,date,amount\". Omit to infer from the header.",
            "type": "string"
          },
          "url": {
            "description": "Public URL of the PDF.",
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "extract_tables",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Fetch a public URL and return clean LLM-ready Markdown from the server-rendered response. This tool does not execute browser JavaScript; for SPA or empty-text pages, use web_search, a browser, or the site's API. Use it after web_search to read a reachable public source, or to ingest a static page for analysis. Example — GET https://ainetcafe.com/t/fetch_page?url=https://example.com",
      "inputSchema": {
        "properties": {
          "url": {
            "description": "The page URL to fetch.",
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "fetch_page",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Full details of one hosted application: what it does, how to use it, measured benchmark scores, source repository, and the URL a human can open to run it. Example — GET https://ainetcafe.com/t/get_app?slug=<slug-from-list_apps>",
      "inputSchema": {
        "properties": {
          "slug": {
            "description": "Application slug, from list_apps.",
            "type": "string"
          }
        },
        "required": [
          "slug"
        ],
        "type": "object"
      },
      "name": "get_app",
      "outputSchema": {
        "properties": {
          "name": {
            "type": "string"
          },
          "open_url": {
            "type": "string"
          },
          "slug": {
            "type": "string"
          }
        },
        "required": [
          "slug",
          "name"
        ],
        "type": "object"
      }
    },
    {
      "description": "Recent runs of one scheduled task: what it returned, whether the result changed, and measured platform cost metadata. User charge is $0.00.",
      "inputSchema": {
        "properties": {
          "limit": {
            "description": "How many recent runs, max 20, default 5.",
            "type": "integer"
          },
          "task_id": {
            "description": "From create_task or list_tasks.",
            "type": "integer"
          }
        },
        "required": [
          "task_id"
        ],
        "type": "object"
      },
      "name": "get_task_runs",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Converts JSON to YAML or YAML to JSON. It works out which one you gave it, so you do not have to say. A parse failure comes back with the parser message instead of silently producing something that looks fine and is not. Use when a config, a CI file, or a Kubernetes manifest needs to be in the other format.",
      "inputSchema": {
        "properties": {
          "text": {
            "description": "The JSON or YAML content.",
            "type": "string"
          },
          "to": {
            "description": "Optional: \"json\" or \"yaml\" to force the direction.",
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "json_yaml",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Decodes the header and payload of a JWT and reports issued-at / expiry as readable timestamps plus seconds remaining. The signature is NOT verified and the response says so — decoding is fine for debugging a token you already hold, but never treat these values as proof of anything; verification needs the secret and belongs in your own service.",
      "inputSchema": {
        "properties": {
          "token": {
            "description": "The JWT string.",
            "type": "string"
          }
        },
        "required": [
          "token"
        ],
        "type": "object"
      },
      "name": "jwt_decode",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "List the open-source AI applications hosted and ready to run at AI NetCafé (ainetcafe.com). Each one normally requires local setup (Docker/Python + your own model API key); here they run pre-configured. Use this to find a tool for a task like translating a PDF with formulas intact, generating a PowerPoint file, polishing an academic paper, or running an autonomous research report. Do not call this first when the request already clearly matches compare_models, translate_pdf, deep_research, or make_slides; call that task tool directly. Example — GET https://ainetcafe.com/t/list_apps",
      "inputSchema": {
        "properties": {
          "category": {
            "description": "Optional filter, e.g. \"office\", \"research\", \"chat\".",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "list_apps",
      "outputSchema": {
        "properties": {
          "apps": {
            "items": {
              "type": "object"
            },
            "type": "array"
          },
          "try_in_browser": {
            "type": "string"
          }
        },
        "required": [
          "apps"
        ],
        "type": "object"
      }
    },
    {
      "description": "List every model currently available in the free beta with reference input/output rates and health metadata. Those rates are platform cost metadata only; every user charge is $0.00 during the beta. Example — GET https://ainetcafe.com/t/list_models",
      "inputSchema": {
        "properties": {
          "tier": {
            "description": "Optional reference tier filter. All currently healthy tiers are available without a user key during the beta.",
            "enum": [
              "free",
              "premium"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "list_models",
      "outputSchema": {
        "properties": {
          "models": {
            "items": {
              "type": "object"
            },
            "type": "array"
          }
        },
        "required": [
          "models"
        ],
        "type": "object"
      }
    },
    {
      "description": "Show scheduled tasks, next run times, run counts, and measured platform cost metadata. User charge is $0.00 during the beta.",
      "inputSchema": {
        "properties": {},
        "required": [],
        "type": "object"
      },
      "name": "list_tasks",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Combines up to 20 CSVs into a single table. Headers do not have to match: columns are unioned and a file missing a column contributes blanks for it, so rows never shift silently — the failure mode that makes hand-merged spreadsheets untrustworthy. Reports each source file row count and checks in code that they sum to the merged total. Use for monthly exports, per-store sheets, or any set of files with the same subject but drifting headers.",
      "inputSchema": {
        "properties": {
          "texts": {
            "description": "Or pass the CSV contents directly as an array.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "urls": {
            "description": "Comma-separated CSV links, at least two.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "merge_tables",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Measured platform cost metadata for one call on each model; your charge is $0.00 during the free beta. Vendors publish per-million-token list prices, but a call's cost depends on how many tokens the model chooses to emit — models differ by an order of magnitude on the same prompt. standard_bench sends an IDENTICAL prompt to every model, so the difference is the model, not the workload — use that to choose a model before bulk work. production_mixed is real traffic and is NOT comparable across models. Free to cite, CC BY 4.0. Example — GET https://ainetcafe.com/t/model_costs",
      "inputSchema": {
        "properties": {
          "days": {
            "description": "Measurement window in days (default 30).",
            "type": "integer"
          }
        },
        "type": "object"
      },
      "name": "model_costs",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Convert a PDF (or a scanned page image) into clean Markdown that keeps headings, lists and tables, and puts multi-column pages in the right reading order. Text-layer PDFs are read exactly and cost far less; images go through a vision model.",
      "inputSchema": {
        "properties": {
          "url": {
            "description": "Public URL of the PDF, or of a page image (png/jpg) for scanned documents.",
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "pdf_to_markdown",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Retrieve previously stored memories, optionally filtered by search query and/or project. Call at the start of work on a known project to restore context: why decisions were made, known fixes, preferences. Example — GET https://ainetcafe.com/t/recall?query=<what+to+remember>  (needs a workspace/key for durable memory)",
      "inputSchema": {
        "properties": {
          "limit": {
            "description": "Max results (default 8, up to 20).",
            "type": "integer"
          },
          "project": {
            "description": "Optional project filter.",
            "type": "string"
          },
          "query": {
            "description": "Optional search terms; omit to list the most recent.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "recall",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Reconciles two sets of records — your books against a bank, platform, or supplier statement. Matches rows on a key column, compares an amount column, and returns three lists: only in A, only in B, and same key but different amount. Amounts are compared in integer cents, so 0.1 + 0.2 never invents a phantom difference for someone to chase. The response also proves the result: the listed differences are re-added and must equal the gap between the two totals, checked in code. Use for month-end close, platform payouts vs orders, or any \"these two numbers should agree and do not\" problem. This is the job people do by hand with VLOOKUP or a groupby and then cannot prove they got right.",
      "inputSchema": {
        "properties": {
          "amount": {
            "description": "Numeric column to compare, e.g. amount.",
            "type": "string"
          },
          "key": {
            "description": "Column name to match rows on, e.g. order_id.",
            "type": "string"
          },
          "text_a": {
            "description": "Or the CSV content of side A directly.",
            "type": "string"
          },
          "text_b": {
            "description": "Or the CSV content of side B directly.",
            "type": "string"
          },
          "url_a": {
            "description": "Link to side A (e.g. your books).",
            "type": "string"
          },
          "url_b": {
            "description": "Link to side B (e.g. the statement).",
            "type": "string"
          }
        },
        "required": [
          "key",
          "amount"
        ],
        "type": "object"
      },
      "name": "reconcile_ledger",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Runs a regular expression against sample text and returns every match with its position and capture groups (named groups included). Use before wiring a pattern into code, instead of guessing whether the escaping survived the trip through JSON and the shell.",
      "inputSchema": {
        "properties": {
          "flags": {
            "description": "Optional flags, e.g. \"gi\". Default \"g\".",
            "type": "string"
          },
          "pattern": {
            "description": "The regular expression, without surrounding slashes.",
            "type": "string"
          },
          "text": {
            "description": "The text to test against.",
            "type": "string"
          }
        },
        "required": [
          "pattern",
          "text"
        ],
        "type": "object"
      },
      "name": "regex_test",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Persist a durable memory: an architecture decision, a stable user preference, a verified bug fix, or an important discovery. The free beta provides a bounded per-caller/workspace memory pool; no personal API key is required. Do not store secrets or raw logs. Example — tools/call remember {\"content\":\"Deploy key rotates monthly\"}",
      "inputSchema": {
        "properties": {
          "content": {
            "description": "The memory itself, self-contained (≤2000 chars).",
            "type": "string"
          },
          "kind": {
            "description": "Category; default \"note\".",
            "enum": [
              "decision",
              "preference",
              "bugfix",
              "discovery",
              "note"
            ],
            "type": "string"
          },
          "project": {
            "description": "Optional project name to scope recall later.",
            "type": "string"
          }
        },
        "required": [
          "content"
        ],
        "type": "object"
      },
      "name": "remember",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Turn diagram-as-code into an image: Mermaid, PlantUML, Graphviz/DOT, C4, Excalidraw and 20+ more (self-hosted Kroki). Returns a hosted SVG/PNG URL you can embed directly in Markdown or HTML. Example — GET \"https://ainetcafe.com/t/render_diagram?source=graph TD;A--%3EB&format=png\"",
      "inputSchema": {
        "properties": {
          "format": {
            "description": "\"svg\" (default) or \"png\".",
            "type": "string"
          },
          "source": {
            "description": "The diagram source code (e.g. a Mermaid flowchart).",
            "type": "string"
          },
          "type": {
            "description": "Diagram language: mermaid (default), plantuml, graphviz, c4plantuml, excalidraw, blockdiag, erd…",
            "type": "string"
          }
        },
        "required": [
          "source"
        ],
        "type": "object"
      },
      "name": "render_diagram",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Convert a SQL statement from one dialect to another — mysql, postgres, sqlite, tsql, oracle, snowflake, bigquery, redshift, spark, hive, presto, trino, duckdb, clickhouse, databricks, doris, starrocks and more. Deterministic parser (sqlglot), not an LLM: the same input always produces the same output, and syntax errors come back with the exact line and column. Use it when migrating queries between databases or debugging dialect-specific syntax.",
      "inputSchema": {
        "properties": {
          "read": {
            "description": "Source dialect, e.g. \"mysql\". Omit to auto-detect from generic SQL.",
            "type": "string"
          },
          "sql": {
            "description": "The SQL statement (or several, separated by semicolons).",
            "type": "string"
          },
          "write": {
            "description": "Target dialect, e.g. \"postgres\", \"bigquery\", \"doris\".",
            "type": "string"
          }
        },
        "required": [
          "sql",
          "write"
        ],
        "type": "object"
      },
      "name": "transpile_sql",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Checks that text parses as JSON, and optionally that required keys are present with the right top-level types. Returns the specific violations, not just true/false. Checks required + types only — not full JSON Schema, and it says so rather than pretending. Use before feeding generated JSON into something that will fail on it.",
      "inputSchema": {
        "properties": {
          "schema": {
            "description": "Optional JSON Schema (as JSON text) — required[] and properties[].type are checked.",
            "type": "string"
          },
          "text": {
            "description": "The JSON to validate.",
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "validate_json",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Search the live web through a self-hosted SearXNG meta-search (aggregates dozens of engines, no tracking). Returns titles, URLs and snippets. Use when you need current information or sources. Example — GET https://ainetcafe.com/t/web_search?query=latest+MCP+spec",
      "inputSchema": {
        "properties": {
          "max_results": {
            "description": "Max results (default 8, up to 20).",
            "type": "integer"
          },
          "query": {
            "description": "The search query.",
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "web_search",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Describe a task in plain language (any language) and get back exactly which tools on this server do it, with ready-to-run example calls — instead of reading the whole catalogue and guessing. Also returns multi-step recipes when a task needs several tools chained (invoices to a ledger, a bank statement reconciled, a messy CSV turned into a deliverable). Deterministic and free: it calls no model, costs nothing, and never runs out of quota. Call this FIRST when you are not sure what this server offers.",
      "inputSchema": {
        "properties": {
          "task": {
            "description": "What you are trying to do, e.g. \"reconcile a bank statement against my books\" or \"把一堆发票整理成能入账的表格\"",
            "type": "string"
          }
        },
        "required": [
          "task"
        ],
        "type": "object"
      },
      "name": "what_can_you_do",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:f45a06e354ea4bd926e6b08976403848e9b3548240ccc93eae55ec85fa5d9f28 | sha256sum