MCP.Market

Identity MCP server

by zekebuilds-lab·io.github.zekebuilds-lab/mcp-identity·v0.7.2

DoI score lookup, vouch event builder, and offline schnorr verify for AI agents.

B78/100grade B
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed Identity yet.

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

Identity tools (3)

write = sends, deletes, buys or posts

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

  • doi_score_lookup

    Fetch a Depth-of-Identity score for a Nostr pubkey from the PowForge oracle. Returns either an L402 challenge (macaroon + bolt11 invoice + price_sats) for the caller to pay, or a Schnorr-signed score envelope when paid auth is supplied. Pricing is 1-2 sats per call.

  • doi_score_verify

    Locally verify a Schnorr-signed DoI score envelope returned by the PowForge oracle. No network call. Default oracle pubkey is hardcoded; override via oracle_pubkey or the ORACLE_PUBKEY env var.

  • doi_sign_vouch

    Build an UNSIGNED kind:33335 PowForge vouch event template. The MCP server intentionally never holds keys — the caller signs externally and publishes the signed event to relays.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan6 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 141 days ago8/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Identity compares

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

Safety score
78/100
higher than 57% of 48,255 servers
Tools
3
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break

What its tools let an agent do: 3 read

Install Identity in Claude Code, Cursor or VS Code

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

claude mcp add mcp-identity -- npx -y @powforge/mcp-identity
Add to Cursor

What the publisher says

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

@powforge/mcp-identity

MCP server that scores any Nostr pubkey's depth-of-identity before your handler runs. Chaintip-anchored Schnorr cert, L402 priced, drop-in for AI agents that need Sybil resistance on top of paid APIs.

npm: npm i @powforge/mcp-identity

Homepage: https://powforge.dev/explorer

Whitepaper: https://powforge.dev/whitepaper

What It Does

Three MCP tools that wrap the PowForge Depth-of-Identity Oracle:

  • doiscorelookup — given a Nostr pubkey (hex or npub), returns multi-dimensional identity score (network, longevity, kinetic-filter cost). L402-priced via the upstream oracle.
  • doisignvouch — builds an unsigned Nostr event for vouching depth-of-identity for another pubkey. Caller signs; oracle counts toward score on observation.
  • doiscoreverify — offline Schnorr verification of a signed DoI cert returned from the oracle. No network.

Why Identity-Anchored Pricing

Most paid-API services charge per-request flat. That fails on agent-to-agent surfaces where:

  1. New agents look identical to scrapers — no signal on intent or risk.
  2. Long-tail abusers extract value cheaper than they impose cost.
  3. Whitelist gating doesn't scale to open agent ecosystems.

DoI gives your server a quantitative number for "how much would it cost to fake this caller's identity at this depth" — anchored to a specific Bitcoin chaintip cert that's non-repudiable. Use it as a multiplier on your L402 macaroon price, a rate-limit input, or a routing key.

Quick Start

npm i @powforge/mcp-identity

Add to your MCP config (Claude Desktop, Cursor, etc):

{
  "mcpServers": {
    "powforge-identity": {
      "command": "npx",
      "args": ["-y", "@powforge/mcp-identity"]
    }
  }
}

Restart the client. Three new tools appear under powforge-identity.

Why Chaintip-Anchored

The score includes a Schnorr signature over (score, dimensions, scorechaintipheight, scorechaintipblockhash). That binds the claim to Bitcoin's kinetic filter — recomputable PageRank scores can be silently rewritten, but a chaintip-anchored cert is a fixed claim against a known time. Verification is offline.

The oracle's falsifiable claim window is documented in the whitepaper.

L402 Pricing

The MCP server transparently handles the L402 macaroon dance with oracle.powforge.dev. First call returns a 402 with a Lightning invoice; the wrapper pays from a wallet you configure (env: LNBITSINVOICEKEY) and retries. No keys, no accounts.

Status

  • v0.7.0 published to npm 2026-04-28.
  • Three tools exposed.
  • Cert format documented in the whitepaper.
  • Oracle availability monitored at https://powforge.dev/oracle/freshness.

License

MIT.

Source

Source lives in a private development repo. Issues, questions, and bug reports welcome here.

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

Identity: common questions

Is Identity MCP server safe?
Mostly: it is graded B (78/100). Read the Identity safety report
How do I install Identity?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Identity need an API key?
No secret keys are declared. It reads 2 settings from the environment.
Is Identity maintained?
The last commit was 178 days ago (2026-05-10). The latest release is v0.7.2.
How does Identity compare with other MCP servers?
safety score 78/100 (higher than 57% of 48,255 servers); tools 3 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

More from zekebuilds-lab →