
RiskRouter MCP server
Which servers in the official MCP registry are RiskRouter's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-26
- Registry nameeu.riskrouter/evidence-logverified in the MCP registry
The registry name sits under riskrouter.eu. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-26
- Tools8
- Server calls itselfriskrouter
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 67 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer135 ms
- Space in an agent's context≈ 788 tokensthe definitions of all its tools (8), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 8 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · seal advice notes at the moment they are written
- not sure · hand a sealed decision record to an auditor or regulator
- can do · check that a stored record has not changed since sealing
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
get_evidence_headThe current signed head of the evidence log: tree size, Merkle root and signature. Save it: any later head must be consistent with it.
get_inclusion_proofProof that the entry at leaf_index is in the tree, optionally at a given tree_size. Checkable offline with the public verifier.
get_consistency_proofProof that the tree at size first is a prefix of the tree at size second (or now): the log never rewrote history.
get_checkpointThe log's signed checkpoint in the C2SP format witnesses cosign (origin, size, root).
get_ledger_attestationThe signed head hash of the hash-chained audit ledger of recorded quotes.
get_usageHow much is recorded, and by how many keys that are not ours. Counts only, nothing about anyone.
record_evidenceRecord 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…
get_chainThe log's signed statement of one completeness chain as of the current head: its length and, for each position, the leaf, the time and the digest. A position nobody showed you is a record left out.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"evidence-log": {
"type": "http",
"url": "https://api.riskrouter.eu/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http riskrouter https://api.riskrouter.eu/mcpclaude.ai, ChatGPT and other clients: add https://api.riskrouter.eu/mcp as a custom connector in the settings.
OpenAPI spec
20 paths, read 2026-10-26. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.