Server definition

Hash: sha256:1c7b8230d205a0dad5c746e41ea6b5424a82a43725cb70a2c816d13f6cdcf1af
What it is: What a remote MCP server returned when asked what it offers: 15 tools

The blob, as servednamed by its sha256

{
  "instructions": "Messy spreadsheets in, clean checkable tables out — and every table tool reads Excel .xlsx natively (read_xlsx / write_xlsx round-trip it; dates come back as YYYY-MM-DD, leading zeros survive). The pipeline: fix_csv_encoding repairs a CSV that opens as garbage in Excel; clean_table dedupes, trims, unifies blank values, splits or transposes columns, and reshapes wide tables into long ones; merge_tables unions several files; diff_tables finds what differs between two tables on a key column (the VLOOKUP job); reconcile_ledger compares money on a shared key in integer cents so 0.1+0.2 never invents a phantom difference; match_transactions reconciles when there is NO shared key — bank statement vs ledger by amount, date window, reference numbers in free text and fuzzy counterparty names, handling split (1:N) and combined (N:1) payments, and refusing to guess when evidence is thin; dedupe_entities finds records that are probably the same company under different names, cross-checked against tax-ID checksums — it never merges, it shows the evidence and lets a human decide. Every result that involves counts or money carries its own arithmetic proof computed in code — if the numbers do not reconcile the response says so instead of handing back a table nobody can check. Only accounting conventions are honoured: (100.00) and 100.00- both read as negative. Nothing in the deterministic tools calls a model, so results are repeatable.",
  "tools": [
    {
      "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": "CSV (first column = labels, second = values) → chart PNG in one call.",
      "inputSchema": {
        "additionalProperties": true,
        "properties": {
          "csv": {},
          "type": {},
          "url": {}
        },
        "type": "object"
      },
      "name": "csv_to_chart",
      "outputSchema": null
    },
    {
      "description": "CSV (text or URL) → JSON array of objects (first row = keys). Returns a .json file.",
      "inputSchema": {
        "additionalProperties": true,
        "properties": {
          "csv": {},
          "url": {}
        },
        "type": "object"
      },
      "name": "csv_to_json",
      "outputSchema": null
    },
    {
      "description": "CSV (text or URL) → GitHub-flavoured Markdown table.",
      "inputSchema": {
        "additionalProperties": true,
        "properties": {
          "csv": {},
          "url": {}
        },
        "type": "object"
      },
      "name": "csv_to_md_table",
      "outputSchema": null
    },
    {
      "description": "Convert a transaction CSV into a .qbo / OFX bank-feed file that QuickBooks and similar accounting software import directly. Needs date, description and amount columns (or debit + credit). Pairs with extract_statement: statement PDF in, importable bank feed out.",
      "inputSchema": {
        "properties": {
          "account_id": {
            "description": "Your account number as the accounting software expects it.",
            "type": "string"
          },
          "bank_id": {
            "description": "Routing / bank identifier, if your import asks for one.",
            "type": "string"
          },
          "csv": {
            "description": "CSV content with a header row.",
            "type": "string"
          },
          "currency": {
            "description": "Three-letter currency code, default USD.",
            "type": "string"
          },
          "url": {
            "description": "Or a link to the CSV.",
            "type": "string"
          }
        },
        "required": [],
        "type": "object"
      },
      "name": "csv_to_qbo",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Find records in a supplier/customer/store list that are probably the SAME entity under different names — \"北京星辰科技有限公司\" vs \"星辰科技(北京)\" — by cross-checking name similarity against hard identifiers: tax ID (统一社会信用代码, checksum-verified), phone, domain, bank account, address. It never merges anything: it returns candidate groups with the evidence for each link, pairs that need human review, and — just as",
      "inputSchema": {
        "additionalProperties": true,
        "properties": {
          "address": {},
          "bank": {},
          "domain": {},
          "name": {},
          "name_threshold": {},
          "phone": {},
          "sheet": {},
          "tax_id": {},
          "text": {},
          "url": {}
        },
        "type": "object"
      },
      "name": "dedupe_entities",
      "outputSchema": null
    },
    {
      "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": "Detect the real encoding of a CSV (GB18030, Shift-JIS, Windows-1252…), repair mojibake (UTF-8 that was read as Latin-1, e.g. \"Ã©\"), and re-emit UTF-8 with a BOM so Excel opens it correctly.",
      "inputSchema": {
        "properties": {
          "text": {
            "description": "Or paste the CSV content directly.",
            "type": "string"
          },
          "url": {
            "description": "Public URL of the CSV.",
            "type": "string"
          }
        },
        "required": [],
        "type": "object"
      },
      "name": "fix_csv_encoding",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "JSON array of objects → CSV file. Flattens keys, quotes fields containing commas.",
      "inputSchema": {
        "additionalProperties": true,
        "properties": {
          "json": {}
        },
        "type": "object"
      },
      "name": "json_to_csv",
      "outputSchema": null
    },
    {
      "description": "Match bank statement lines to ledger/invoice entries when there is NO shared key — by amount, date window, reference numbers found inside free-text descriptions, and fuzzy counterparty names (\"北京XX科技\" vs \"XX科技(北京)\"). Handles split payments (one invoice paid in instalments, 1:N) and combined payments (one transfer covering several invoices, N:1). Its rule is: never guess — a pair is only auto-match",
      "inputSchema": {
        "additionalProperties": true,
        "properties": {
          "date_window_days": {},
          "fee_tolerance": {},
          "max_group_size": {},
          "sheet_a": {},
          "sheet_b": {},
          "text_a": {},
          "text_b": {},
          "url_a": {},
          "url_b": {}
        },
        "type": "object"
      },
      "name": "match_transactions",
      "outputSchema": null
    },
    {
      "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": "Read an Excel .xlsx workbook (by URL) into rows — every sheet, or one you name. Returns cell values (not formula text), dates as YYYY-MM-DD instead of Excel serial numbers, and keeps leading zeros so ID/postcode columns are not silently mangled. Says plainly which sheet it used, which sheets are hidden, and where merged cells left blanks, instead of guessing for you.",
      "inputSchema": {
        "additionalProperties": true,
        "properties": {
          "inline": {},
          "keep_formulas": {},
          "max_rows": {},
          "preview_rows": {
            "type": "number"
          },
          "sheet": {},
          "url": {}
        },
        "type": "object"
      },
      "name": "read_xlsx",
      "outputSchema": null
    },
    {
      "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": "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"
      }
    },
    {
      "description": "Build an Excel .xlsx file from rows (CSV text or JSON arrays), optionally several sheets at once. Numbers are written as real numbers so they sum in Excel, while values with leading zeros stay text so IDs and postcodes survive the round trip.",
      "inputSchema": {
        "additionalProperties": true,
        "properties": {
          "sheet_name": {},
          "sheets": {},
          "text": {},
          "url": {}
        },
        "type": "object"
      },
      "name": "write_xlsx",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:1c7b8230d205a0dad5c746e41ea6b5424a82a43725cb70a2c816d13f6cdcf1af | sha256sum