MCP.Market

Claims MCP server

by dgonzap30·io.github.dgonzap30/claims-mcp·v0.1.0
No reviews yet

A claims memory for agents: assert beliefs, let them decay, surface contradictions.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars43 downloads/wk

Reviews

Write one

Nobody has reviewed Claims yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Claims tools (6)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • claim_add

    Assert a claim about an entity (idempotent on entity+kind+claim). Re-asserting updates it.

  • claim_confirm

    Mark a claim as re-confirmed now (resets decay, reactivates it). Optionally set a new confidence.

  • claim_retract

    Retire a claim. It stays in the store but no longer takes part in decay or contradiction checks.

  • claim_search

    Find claims whose text or entity contains the query (case-insensitive).

  • claims_contradictions

    List conflicts among active claims (duplicate priority ranks, multiple status claims per entity). Optionally pass observed weekly ranks to also detect sustained rank drops.

  • claims_decayed

    Active claims whose confidence has decayed past a staleness threshold (0..1, default 0.5), stalest first.

Public scan report

scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it

no findings
  • Code scan11 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 17 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Claims compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 93% of 48,243 servers
Tools
6
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
43
more than 33% of 12,306 servers with a package

What its tools let an agent do: 6 read

Install Claims in Claude Code, Cursor or VS Code

Runs npx -y claims-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add claims-mcp -- npx -y claims-mcp
Add to Cursor

What the publisher says

From the Claims repository's README, as published. We do not edit it. Read it on GitHub

claims-mcp

A small memory for agents that treats what it knows as claims that age. You assert a claim about an entity ("acme is priority #1", "the launch is on track"), each claim decays on a half-life set by how volatile it is, and the server tells you which claims have gone stale and which contradict each other.

It is a stdio MCP server plus a CLI over one local SQLite file. No network, no accounts.

Runtime: Bun. v0 uses bun:sqlite, so it runs on Bun ≥ 1.1, not plain Node. A Node build (node:sqlite) is a possible follow-up.

Model

A claim's identity is (entity, kind, claim): asserting it again updates it rather than duplicating.

MCP tools

Resource: claims://all (every claim as JSON).

observed is { "signals": [{ "": [ranknow, rank1periodago, ...] }, ...], "validPeriods": [true, ...] }. You supply the observations (commit counts, time spent, anything you can rank); the server does not collect them.

Use

bun install

Add to an MCP client (Claude Code shown):

claude mcp add claims -- bun /path/to/claims-mcp/src/mcp.ts

The database lives at ~/.claims-mcp/claims.db; override with --db or CLAIMSMCPDB.

CLI:

bun src/cli.ts add acme priority slow 0.8 "acme comes first" --rank 1
bun src/cli.ts search comes
bun src/cli.ts stale 0.5
bun src/cli.ts contradictions
bun src/cli.ts confirm <id>
bun src/cli.ts retract <id>

Development

bun test          # 19 tests, synthetic claims only
bun run typecheck
bun run audit     # publish gate: home paths, private names, secret patterns

Set AUDIT_TERMS="name1|name2" to add your own private names to the audit.

Provenance

Not a straight extraction. The decay curve and the rank-drop rule are ported from a personal agent memory (rank-drop now takes caller-supplied observations); the duplicate-rank and status-conflict rules are new claim-vs-claim logic written for this package. It shares no code, data or storage with the original.

Licence

MIT

Nothing above is checked by us. What we check is on the safety report.

Claims: common questions

Is Claims MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Claims safety report
How do I install Claims?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Claims need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Claims maintained?
The last commit was 37 days ago (2026-09-29). The latest release is v0.1.0.
How does Claims compare with other MCP servers?
safety score 92/100 (higher than 93% of 48,243 servers); tools 6 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.