protogrid
Sign inAdd to your agent

Search / io.github.louissarvin/proctor

proctor

L0· runs locally

Human oversight for AI agents: block a tool call on a verified human, with on-chain proof.

v1.0.0 · active · repository · descriptor JSON · versions

Runs on your machine: something must execute the package.Only local packages are published (npm, PyPI, OCI, …). The registry never executes them, so tools are unknown until you run it.
Quality–not scored
Trust87of 100
Packages1
Tools seen0

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "proctor": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "HEDERA_AGENT_KEY": "${HEDERA_AGENT_KEY}"
      }
    }
  }
}
claude mcp add proctor -e "HEDERA_AGENT_KEY=${HEDERA_AGENT_KEY}" -- npx -y [email protected]
[mcp_servers.proctor]
command = "npx"
args = ["-y", "[email protected]"]
env = { "HEDERA_AGENT_KEY" = "${HEDERA_AGENT_KEY}" }

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "proctor": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "[email protected]"
      ],
      "enabled": true,
      "environment": {
        "HEDERA_AGENT_KEY": "{env:HEDERA_AGENT_KEY}"
      }
    }
  }
}
{
  "mcpServers": {
    "proctor": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "HEDERA_AGENT_KEY": "${HEDERA_AGENT_KEY}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=proctor&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsInByb2N0b3ItbWNwQDEuMC4wIl0sImVudiI6eyJIRURFUkFfQUdFTlRfS0VZIjoiJHtIRURFUkFfQUdFTlRfS0VZfSJ9fQ%3D%3D"
}
{
  "servers": {
    "proctor": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "HEDERA_AGENT_KEY": "${HEDERA_AGENT_KEY}"
      }
    }
  }
}
{
  "mcpServers": {
    "proctor": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "HEDERA_AGENT_KEY": "${HEDERA_AGENT_KEY}"
      }
    }
  }
}
extensions:
  "proctor":
    enabled: true
    name: "proctor"
    type: stdio
    cmd: "npx"
    args:
      - "-y"
      - "[email protected]"
    envs:
      "HEDERA_AGENT_KEY": "${HEDERA_AGENT_KEY}"
    timeout: 300

Placeholders to fill from your own secret store: ${HEDERA_AGENT_KEY}. The registry never accepts secret values.

This is a local package: the command runs on your machine.

Quality – / 100not scored

Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.

protocoln/a · weight 25
  • n/a
    protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygienen/a · weight 30
  • n/a
    tools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool list unknown
dependencies50 · weight 15
  • fail
    deps.known_vulns5 advisories to act on (malicious, or rated high or critical with a fix available): GHSA-5375-pq7m-f5r2 in @grpc/[email protected] (indirect, fixed in 1.12.7), GHSA-99f4-grh7-6pcq in @grpc/[email protected] (indirect, fixed in 1.12.7), GHSA-m9gg-hp2v-232j in @grpc/[email protected] (indirect, fixed in 1.13.6), ...; 6 more of lower severity or without a fix
  • n/a
    deps.mcp_sdk_versionthe official MCP SDK is not in the dependency graph
  • pass
    deps.resolvable[email protected] resolved: 109 packages

Tool list unknown · checked 2026-10-20 05:13 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 87 / 100

provenance80
livenessn/a
freshness85
hygiene100

+repository +namespace-matches-repo ~liveness-unmeasured ~updated-40d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Dependencies

[email protected] npm108 dependencies, resolved · advisories checked 2026-10-19

advisoryseveritypackagefixed in
GHSA-5375-pq7m-f5r2@grpc/grpc-js: A malformed request can cause a server crashhigh@grpc/[email protected]indirectfixed in 1.12.7
GHSA-99f4-grh7-6pcq@grpc/grpc-js: An incoming malformed compressed message can cause a client or server crashhigh@grpc/[email protected]indirectfixed in 1.12.7
GHSA-m9gg-hp2v-232j@grpc/grpc-js: In certain configurations, getAuthContext can return unauthorized certificates as though they were authorizedhigh@grpc/[email protected]indirectfixed in 1.13.6
GHSA-wcpc-wj8m-hjx6protobufjs: Denial of service through unbounded Any expansion during JSON conversionhigh[email protected]indirectfixed in 8.4.1
GHSA-96hv-2xvq-fx4pws: Memory exhaustion DoS from tiny fragments and data chunkshigh[email protected]indirectfixed in 8.21.0
GHSA-94rc-8x27-4472protobufjs: Memory amplification from preserved unknown fields in binary decodemoderate[email protected]indirectfixed in 8.5.0
GHSA-f38q-mgvj-vph7protobufjs : Schema-derived names can shadow runtime-significant propertiesmoderate[email protected]indirectfixed in 8.6.0
GHSA-j3f2-48v5-ccwwprotobufjs: Denial of Service via infinite loop in .proto option parsingmoderate[email protected]indirectfixed in 8.6.6
GHSA-jfj6-75fj-8934protobufjs: Text Format string map parsing can mutate returned map object prototypemoderate[email protected]indirectfixed in 8.6.5
GHSA-58qx-3vcg-4xpxws: Uninitialized memory disclosuremoderate[email protected]indirectfixed in 8.20.1

1 more advisories in the dependencies endpoint.

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.

Endpoints

packageregistryversionruntimesecrets
proctor-mcpnpm1.0.0–HEDERA_AGENT_KEY

Tools (0)

No tools observed. Local packages are never executed by the registry.

Schemas: list_tools.

Similar MCP servers

  • prove-itL0
    io.github.ark-forge/prove-it

    Free public benchmark for AI agents: compliance tasks, every claim checked against signed receipts

  • TAPR2quality 83
    tech.human/tap

    Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval.

  • agentlockR1
    io.github.Olum289/agentlock

    Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.

  • verify402L0
    io.github.a32116150-ctrl/verify402-mcp

    Preflight safety gate and x402 on-chain truth verification tools for AI agents

  • shukaL0
    io.github.cdonoyan/shuka

    Universal trust attestation for AI agents: create, verify, and negotiate Shuka trust proofs.

  • delegoL0
    io.github.Delego-Dev/delego

    Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.

Official server.json
{
  "name": "io.github.louissarvin/proctor",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "version": "1.0.0",
  "packages": [
    {
      "version": "1.0.0",
      "transport": {
        "type": "stdio"
      },
      "identifier": "proctor-mcp",
      "registryType": "npm",
      "environmentVariables": [
        {
          "name": "PROCTOR_API",
          "format": "string",
          "description": "Base URL of the Proctor gate. Defaults to http://localhost:3700."
        },
        {
          "name": "HEDERA_AGENT_ID",
          "format": "string",
          "description": "Hedera account id of the paying agent, e.g. 0.0.12345. Set this with HEDERA_AGENT_KEY to settle a real x402 payment. Omit both and the tool falls back to Proctor's operator endpoint, which opens a real decision but settles nothing."
        },
        {
          "name": "HEDERA_AGENT_KEY",
          "format": "string",
          "isSecret": true,
          "description": "ECDSA private key for HEDERA_AGENT_ID. Spends money: scope it to a funded testnet account and nothing else."
        },
        {
          "name": "AGENT_ALLOWED_TOKENS",
          "format": "string",
          "description": "Comma-separated HTS token ids this agent may pay in. The agent's own guard: it refuses assets its operator never approved."
        }
      ]
    }
  ],
  "repository": {
    "url": "https://github.com/louissarvin/proctor",
    "source": "github",
    "subfolder": "mcp"
  },
  "description": "Human oversight for AI agents: block a tool call on a verified human, with on-chain proof."
}