evidence-log

Tamper-evident evidence log: signed heads, proofs, and recording salted digests of your records.

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
60%
Naming quality
100%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~560Tokens (tool definitions)
~403 BTypical response size
Minimal attention impact (0.44% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "evidence-log": {
      "url": "https://api.riskrouter.eu/mcp"
    }
  }
}

Remote endpoints

https://api.riskrouter.eu/mcpstreamable-http

What it can do

Tool inventory

Tools (7)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟡get_evidence_head

The current signed head of the evidence log: tree size, Merkle root and signature. Save it: any later head must be consistent with it.

Input Schema

{
  "type": "object",
  "properties": {}
}
🟢get_inclusion_proof(leaf_index, tree_size)

Proof that the entry at leaf_index is in the tree, optionally at a given tree_size. Checkable offline with the public verifier.

Input Schema

{
  "type": "object",
  "properties": {
    "leaf_index": {
      "type": "integer",
      "minimum": 0,
      "description": "Position of the entry in the log."
    },
    "tree_size": {
      "type": "integer",
      "minimum": 0,
      "description": "Optional: the tree size to prove against."
    }
  },
  "required": [
    "leaf_index"
  ]
}
🟢get_consistency_proof(first, second)

Proof that the tree at size first is a prefix of the tree at size second (or now): the log never rewrote history.

Input Schema

{
  "type": "object",
  "properties": {
    "first": {
      "type": "integer",
      "minimum": 0,
      "description": "A tree size you hold a head for."
    },
    "second": {
      "type": "integer",
      "minimum": 0,
      "description": "Optional: a later tree size."
    }
  },
  "required": [
    "first"
  ]
}
🟢get_checkpoint

The log's signed checkpoint in the C2SP format witnesses cosign (origin, size, root).

Input Schema

{
  "type": "object",
  "properties": {}
}
🟢get_ledger_attestation

The signed head hash of the hash-chained audit ledger of recorded quotes.

Input Schema

{
  "type": "object",
  "properties": {}
}
🟢get_usage

How much is recorded, and by how many keys that are not ours. Counts only, nothing about anyone.

Input Schema

{
  "type": "object",
  "properties": {}
}
🟡record_evidence(record_digest, kind)

Record the SHA-256 of a decision record you keep yourself, so it can later be shown to be unchanged. Send the digest and a short kind, never the record. Needs your RiskRouter key in the Authorization header of the MCP connection. Entries are permanent.

Input Schema

{
  "type": "object",
  "properties": {
    "record_digest": {
      "type": "string",
      "pattern": "^[0-9a-f]{64}$",
      "description": "SHA-256 of your salted record, lowercase hex. Never the record itself."
    },
    "kind": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9.-]{0,39}$",
      "description": "A short tag such as ai.decision."
    }
  },
  "required": [
    "record_digest",
    "kind"
  ]
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded7 tools