Server definition

Hash: sha256:2332ba9586957e045ef70824246b23e6da5e5e71f36dc93c6948d5480fcde875
What it is: What a remote MCP server returned when asked what it offers: 7 tools

The blob, as servednamed by its sha256

{
  "instructions": "Safety verdicts for AI agents, pay-per-call. tools/list is free; tools/call forwards your Authorization (a paygent credits key) to the paid gate, or returns payment instructions if absent.",
  "tools": [
    {
      "description": "Untrusted-content guardrail for agents: submit a blob of text you are about to feed to your own LLM (scraped web content, a tool result, another agent's message) and get a machine-enforceable verdict - is this a prompt-injection / jailbreak / data-exfiltration / tool-hijack attempt? Returns a risk level, the detected classes with spans, the unicode obfuscation it found (zero-width, bidi-override, tag-chars, homoglyphs), and a SANITIZED copy safe to feed onward. Hybrid: a deterministic, uninjectable pattern engine (authoritative) plus an LLM classifier that can only raise the risk, never clear a flag. Detection of known injection classes - not a proof of safety. [security; up to 15c/call]",
      "inputSchema": {
        "properties": {
          "content": {
            "description": "The untrusted text to scan before you feed it to your LLM.",
            "type": "string"
          },
          "context": {
            "description": "Optional: where the content came from (url, tool name, sender) - context only.",
            "type": "string"
          }
        },
        "required": [
          "content"
        ],
        "type": "object"
      },
      "name": "inject-guard",
      "outputSchema": null
    },
    {
      "description": "Turn a git diff into a clear PR description or release notes. [dev-tools; up to 30c/call]",
      "inputSchema": {
        "properties": {
          "diff": {
            "description": "Unified git diff to summarise",
            "type": "string"
          },
          "style": {
            "description": "e.g. conventional, changelog, executive",
            "type": "string"
          }
        },
        "required": [
          "diff"
        ],
        "type": "object"
      },
      "name": "pr-summary",
      "outputSchema": null
    },
    {
      "description": "Leaked-credential guardrail for agents: submit a blob you are about to commit, log, post, or hand to another tool (a diff, a config, an .env, an LLM output) and get a machine-enforceable verdict - does it contain a live secret? Detects cloud keys (AWS), VCS tokens (GitHub/GitLab), provider API keys (Stripe, OpenAI, Anthropic, Google, Slack), private-key blocks, JWTs, and credentials embedded in URLs, plus high-entropy key=value assignments. Returns a risk level, the detected classes with a MASKED locator (never the secret itself, so the verdict cannot re-leak), and a REDACTED copy safe to emit onward. Deterministic, sub-second, never fetches. Detection of known secret formats - not a proof of cleanliness. [security; up to 200c/call]",
      "inputSchema": {
        "properties": {
          "content": {
            "description": "The text to scan for leaked secrets (diff, config, .env, log line, LLM output).",
            "type": "string"
          }
        },
        "required": [
          "content"
        ],
        "type": "object"
      },
      "name": "secret-scan",
      "outputSchema": null
    },
    {
      "description": "Security review of a code snippet or diff. Returns structured findings (severity, CWE, location, remediation). [security; up to 75c/call]",
      "inputSchema": {
        "properties": {
          "code": {
            "description": "Source code or unified diff to review",
            "type": "string"
          },
          "context": {
            "description": "Optional context about the code",
            "type": "string"
          },
          "language": {
            "description": "Language hint, e.g. typescript, python",
            "type": "string"
          }
        },
        "required": [
          "code"
        ],
        "type": "object"
      },
      "name": "secure-code-review",
      "outputSchema": null
    },
    {
      "description": "Pre-sign safety oracle for agent wallets: submit the transaction or EIP-712 message you are about to sign and get a machine-enforceable verdict. Decodes the calldata/typed-data, flags the drainer toolkit (unlimited approvals, setApprovalForAll, permit/permit2 + EIP-3009 to an unexpected party, transferFrom draining an unnamed account, ownership transfer, raw ETH to a stranger), and binds the decoded action to your stated intent - only a fully pinned, clean action is auto-sign-safe. Fails closed: an undecodable on-chain call is cautioned and an unrecognized off-chain signature grant is blocked. Deterministic, sub-second, no endpoint fetch. It vouches that the action matches what you said; it does NOT vouch that a counterparty is trustworthy. [security; up to 200c/call]",
      "inputSchema": {
        "properties": {
          "context": {
            "description": "Optional free-form context.",
            "type": "string"
          },
          "expected": {
            "description": "Your stated intent. Supplying it lets the verdict BIND the action; only a fully bound, clean action is auto-sign-safe. For an allowance, you MUST supply maxAmount; for a transferFrom, supply `from`.",
            "properties": {
              "asset": {
                "description": "Token contract you intend to touch.",
                "type": "string"
              },
              "chainId": {
                "description": "Chain you intend to act on.",
                "type": "number"
              },
              "contract": {
                "description": "Contract you intend to call.",
                "type": "string"
              },
              "from": {
                "description": "Account whose funds you intend to move (transferFrom / EIP-3009).",
                "type": "string"
              },
              "maxAmount": {
                "description": "Atomic ceiling you intend to expose (required to auto-sign an allowance).",
                "type": "string"
              },
              "recipient": {
                "description": "Address you intend to send to.",
                "type": "string"
              },
              "spender": {
                "description": "Address you intend to approve.",
                "type": "string"
              }
            },
            "type": "object"
          },
          "spendPolicy": {
            "description": "Optional buyer spend policy (context only).",
            "type": "object"
          },
          "tx": {
            "description": "An EVM transaction you are about to sign.",
            "properties": {
              "chainId": {
                "description": "EIP-155 chain id (e.g. 8453 for Base).",
                "type": "number"
              },
              "data": {
                "description": "Calldata hex (0x...). Omit for a plain ETH transfer.",
                "type": "string"
              },
              "to": {
                "description": "Target contract / recipient (0x address).",
                "type": "string"
              },
              "value": {
                "description": "Wei to send, decimal or 0x.",
                "type": "string"
              }
            },
            "type": "object"
          },
          "typedData": {
            "description": "An EIP-712 message you are about to sign (the off-chain drainer surface: permit, Permit2, EIP-3009). { domain, types, primaryType, message }.",
            "type": "object"
          }
        },
        "type": "object"
      },
      "name": "sign-guard",
      "outputSchema": null
    },
    {
      "description": "Pre-execution safety oracle for agent actions: submit the tool call you are about to run (shell, http, sql, file, code, env) plus your stated intent, and get a machine-enforceable verdict before you execute it. Decodes what the call does, flags the danger toolkit (rm -rf, reverse shell, curl|sh, SSRF to cloud metadata, credential reads, DROP/DELETE-without-WHERE, path traversal, dynamic eval), and binds it to your intent (allowedHosts/allowedPaths/readOnly/noNetwork) - only a fully pinned, clean, intent-matched call is auto-exec-safe. Hybrid: a deterministic, uninjectable detector engine (authoritative) plus an LLM classifier that can only raise the risk. Fails closed. Detection of known-dangerous patterns, not a proof of safety; it never executes the call. [security; up to 8c/call]",
      "inputSchema": {
        "properties": {
          "call": {
            "description": "The tool call you are about to execute.",
            "properties": {
              "body": {
                "description": "http: request body (context).",
                "type": "string"
              },
              "command": {
                "description": "shell: the full command line.",
                "type": "string"
              },
              "kind": {
                "description": "The kind of action.",
                "enum": [
                  "shell",
                  "http",
                  "sql",
                  "file",
                  "code",
                  "env"
                ],
                "type": "string"
              },
              "language": {
                "description": "code: the language.",
                "type": "string"
              },
              "method": {
                "description": "http: HTTP method.",
                "type": "string"
              },
              "name": {
                "description": "env: the variable name.",
                "type": "string"
              },
              "op": {
                "description": "file: read|write|delete|move. env: read|write.",
                "type": "string"
              },
              "path": {
                "description": "file: the target path.",
                "type": "string"
              },
              "query": {
                "description": "sql: the SQL statement.",
                "type": "string"
              },
              "source": {
                "description": "code: the source to run.",
                "type": "string"
              },
              "url": {
                "description": "http: the target URL.",
                "type": "string"
              }
            },
            "required": [
              "kind"
            ],
            "type": "object"
          },
          "context": {
            "description": "Optional: where the task/input came from (untrusted source label).",
            "type": "string"
          },
          "expected": {
            "description": "Machine-checkable constraints. Supplying them lets the verdict BIND the call; only a positively-scoped, satisfied call is auto-exec-safe.",
            "properties": {
              "allowedHosts": {
                "description": "http: the only hosts you intend to reach (required to auto-exec a networked call).",
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              "allowedPaths": {
                "description": "file: the only paths you intend to touch (required to auto-exec a file write).",
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              "noNetwork": {
                "description": "the call must not reach the network.",
                "type": "boolean"
              },
              "readOnly": {
                "description": "the call must not mutate state (set false to auto-exec a mutating call).",
                "type": "boolean"
              }
            },
            "type": "object"
          },
          "intent": {
            "description": "What this call is for (natural language). Used by the classifier for intent-mismatch.",
            "type": "string"
          }
        },
        "required": [
          "call"
        ],
        "type": "object"
      },
      "name": "tool-call-guard",
      "outputSchema": null
    },
    {
      "description": "Vet an x402 counterparty before settling USDC: scores the advertised payment requirements AND (when supplied) the EIP-3009 authorization you are about to sign. Returns a machine-enforceable trust verdict (per-entry scores, coverage-honest trustScore, spend-constraint + tamper-evident fingerprint) for buyer agents and wallet/spend-policy layers. No endpoint fetch. [security; up to 200c/call]",
      "inputSchema": {
        "properties": {
          "context": {
            "description": "Optional free-form context.",
            "type": "string"
          },
          "endpointUrl": {
            "description": "Resource URL being paid (context only; never fetched).",
            "type": "string"
          },
          "expected": {
            "description": "Optional caller expectations.",
            "properties": {
              "asset": {
                "description": "Expected asset contract address",
                "type": "string"
              },
              "chainId": {
                "type": "number"
              },
              "identity": {
                "type": "string"
              },
              "maxAmountAtomic": {
                "type": "string"
              },
              "network": {
                "type": "string"
              },
              "payTo": {
                "type": "string"
              }
            },
            "type": "object"
          },
          "paymentPayload": {
            "description": "The UNSIGNED EIP-3009 authorization the buyer is about to sign: { authorization|message: {from,to,value,validAfter,validBefore,nonce}, domain: {name,version,chainId,verifyingContract} }. Lets the audit bind the menu to the actual charge (server-enforced to/value/verifyingContract/chainId). Omit to vet requirements only - but then the verdict is never auto-settle-safe."
          },
          "paymentRequirements": {
            "description": "The x402 payment requirements from the counterparty: the 402 `accepts` array, or a single object."
          },
          "selectedOptionIndex": {
            "description": "Index in the accepts array the buyer intends to settle (default 0). The verdict is scoped to it.",
            "type": "number"
          },
          "serverMetadata": {
            "description": "Optional server metadata the caller already holds (context only; not fetched)."
          },
          "spendPolicy": {
            "description": "Optional buyer spend policy to evaluate against and to pin facilitators.",
            "properties": {
              "allowedAssets": {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              "allowedFacilitators": {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              "allowedNetworks": {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              "maxUsd": {
                "type": "number"
              }
            },
            "type": "object"
          }
        },
        "required": [
          "paymentRequirements"
        ],
        "type": "object"
      },
      "name": "x402-trust-audit",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:2332ba9586957e045ef70824246b23e6da5e5e71f36dc93c6948d5480fcde875 | sha256sum