protogrid

Search / ai.helixar/mcp

Helixar Security

not classified

Security tools for AI agents: scan MCP servers, validate HDP delegation chains, audit releases.

v0.0.1 · active · repository · website · descriptor JSON · versions

Not classified yet.The remote endpoints have not been probed successfully, or the listing has nothing to connect to.
Quality71needs work
Trust88of 100
Uptime, 30 days95%
Latency p50197 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "helixar": {
      "type": "http",
      "url": "https://mcp.helixar.ai/mcp"
    }
  }
}
claude mcp add --transport http helixar https://mcp.helixar.ai/mcp
[mcp_servers.helixar]
url = "https://mcp.helixar.ai/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "helixar": {
      "type": "remote",
      "url": "https://mcp.helixar.ai/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "helixar": {
      "type": "http",
      "url": "https://mcp.helixar.ai/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=helixar&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLmhlbGl4YXIuYWkvbWNwIn0%3D"
}
{
  "servers": {
    "helixar": {
      "type": "http",
      "url": "https://mcp.helixar.ai/mcp"
    }
  }
}
{
  "mcpServers": {
    "helixar": {
      "httpUrl": "https://mcp.helixar.ai/mcp"
    }
  }
}
extensions:
  "helixar":
    enabled: true
    name: "helixar"
    type: streamable_http
    uri: "https://mcp.helixar.ai/mcp"
    timeout: 300

Quality 71 / 100needs work

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 hygiene71 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • fail
    tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: helixar_inspect_mcp (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); helixar_hdp_validate (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
  • pass
    tools.token_costabout 397 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool history not recorded yet
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

2 tools, about 397 tokens to load them all · checked 2026-10-19 10:52 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 88 / 100

provenance85
liveness98
freshness65
hygiene100

+repository +dns-namespace +website +reachable +uptime-95% ~updated-175d-ago

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://mcp.helixar.ai/mcp streamable-httpunknownyes95%197 ms–2026-10-19

Tools (2)

helixar_hdp_validateValidate an HDP delegation chain against IETF draft-helixar-hdp-agentic-delegation-00. Surfaces scope escalations, depth violations, expired hops, missing signatures. Every output cites the IETF draft and Zenodo DOI.
helixar_inspect_mcpScan an MCP server (URL or raw manifest JSON) against Helixar's Sentinel detection rules. Returns risk score, findings, and a Claude-generated security brief. Quick mode is free + authless (top 8 rules); deep mode runs all 26 rules with an api_key.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "ai.helixar/mcp",
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "tool": "manual",
      "notes": "Workers deployment exposes 2 of 3 tools (helixar_inspect_mcp, helixar_hdp_validate). The third tool (helixar_releaseguard) wraps a Go binary and is stdio-only — install the npm package locally for the full set.",
      "version": "0.0.1"
    }
  },
  "title": "Helixar Security",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.helixar.ai/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.0.1",
  "repository": {
    "url": "https://github.com/Helixar-AI/helixar-mcp",
    "source": "github"
  },
  "websiteUrl": "https://helixar.ai/connect",
  "description": "Security tools for AI agents: scan MCP servers, validate HDP delegation chains, audit releases."
}