protogrid

Search / io.github.dth0108/bies-guardian

bies-guardian

not classified

Deterministic sealed verdicts on public claims and startup ideas (0-LLM claim-safety guardian).

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

Not classified yet.The remote endpoints have not been probed successfully, or the listing has nothing to connect to.
Quality85good
Trust43of 100
Uptime, 30 days85%
Latency p50571 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "bies-guardian": {
      "type": "http",
      "url": "https://bies.io/mcp"
    }
  }
}
claude mcp add --transport http bies-guardian https://bies.io/mcp
[mcp_servers.bies-guardian]
url = "https://bies.io/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "bies-guardian": {
      "type": "remote",
      "url": "https://bies.io/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "bies-guardian": {
      "type": "http",
      "url": "https://bies.io/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=bies-guardian&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYmllcy5pby9tY3AifQ%3D%3D"
}
{
  "servers": {
    "bies-guardian": {
      "type": "http",
      "url": "https://bies.io/mcp"
    }
  }
}
{
  "mcpServers": {
    "bies-guardian": {
      "httpUrl": "https://bies.io/mcp"
    }
  }
}
extensions:
  "bies-guardian":
    enabled: true
    name: "bies-guardian"
    type: streamable_http
    uri: "https://bies.io/mcp"
    timeout: 300

Quality 85 / 100good

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
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 hygiene86 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations3 of 3 tools declare readOnlyHint or destructiveHint
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: claim_safety_verdict (destructiveHint, idempotentHint); idea_rehearsal (destructiveHint, idempotentHint); rejudge_claims (destructiveHint, idempotentHint)
  • pass
    tools.token_costabout 689 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability100 · weight 15
  • pass
    stability.changesno tool changes in 30 days
  • pass
    stability.rug_pullno tool changed its meaning under the same name
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

3 tools, about 689 tokens to load them all · tool set 2aab118fd0d5 · checked 2026-10-20 14:54 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 43 / 100

no-repositoryunreachable
provenance45
liveness0
freshness65
hygiene80

+website -unreachable(8 failures) ~updated-108d-ago -no-repository

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

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://bies.io/mcp streamable-httpnoneno (8 failures)85%571 ms2025-06-182026-10-01

Tools (3)

claim_safety_verdictread-onlyDeterministic, sealed pre-publication verdict on a PUBLIC claim (marketing copy, product page, ad headline). Returns per-claim verdict (PASS / CONDITIONAL_PASS / STOP), severity, and a reproducible replay_hash. A 0-LLM rules engine grounded in KR 표시광고법 / US FTC claim categories — NOT legal advice, NOT market proof or launch approval. Call this before a public claim ships.
idea_rehearsalread-onlyDeterministic decision-rehearsal verdict on a founder's BUSINESS IDEA (not a public claim). Returns a graded verdict (Conditional GO / Clear one critical gate / Confirm the headwind / Verify the basics / Redesign the structure / Firm up the inputs / Hold·Redesign) driven by the venture's structural signals, with a reproducible seal. Classification is retrieval-grounded; the verdict and seal are reproducible. NOT market proof, NOT investment advice. Use to pressure-test an idea before committing.
rejudge_claimsread-onlyRe-judge a prior claim-safety verdict against new EVIDENCE. Pass the 'artifact' returned by claim_safety_verdict plus 'observations' (what happened). The top-level verdict NEVER changes on evidence (conservative by design); what moves is 4 axes — now-sayable lines (behind your owner-gate), permanently issuer-only claims, claims still short on evidence, and new risks. Deterministic, sealed, stateless (nothing stored).

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "io.github.dth0108/bies-guardian",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://bies.io/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://bies.io",
  "description": "Deterministic sealed verdicts on public claims and startup ideas (0-LLM claim-safety guardian)."
}