protogrid

Search / io.github.owenkingva-web/vulnhunt

VulnHunt Security Intelligence

not classified

Read-only smart-contract security intelligence for autonomous agents.

v1.0.0 · active · descriptor JSON · versions

Not classified yet.The remote endpoints have not been probed successfully, or the listing has nothing to connect to.
Quality83good
Trust44of 100
Uptime, 30 days76%
Latency p50286 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "vulnhunt": {
      "type": "http",
      "url": "https://vulnhunt-agent-api-production.up.railway.app/mcp"
    }
  }
}
claude mcp add --transport http vulnhunt https://vulnhunt-agent-api-production.up.railway.app/mcp
[mcp_servers.vulnhunt]
url = "https://vulnhunt-agent-api-production.up.railway.app/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "vulnhunt": {
      "type": "remote",
      "url": "https://vulnhunt-agent-api-production.up.railway.app/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "vulnhunt": {
      "type": "http",
      "url": "https://vulnhunt-agent-api-production.up.railway.app/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=vulnhunt&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vdnVsbmh1bnQtYWdlbnQtYXBpLXByb2R1Y3Rpb24udXAucmFpbHdheS5hcHAvbWNwIn0%3D"
}
{
  "servers": {
    "vulnhunt": {
      "type": "http",
      "url": "https://vulnhunt-agent-api-production.up.railway.app/mcp"
    }
  }
}
{
  "mcpServers": {
    "vulnhunt": {
      "httpUrl": "https://vulnhunt-agent-api-production.up.railway.app/mcp"
    }
  }
}
extensions:
  "vulnhunt":
    enabled: true
    name: "vulnhunt"
    type: streamable_http
    uri: "https://vulnhunt-agent-api-production.up.railway.app/mcp"
    timeout: 300

Quality 83 / 100good

protocol88 · weight 25
  • pass
    protocol.modernsupports 2026-07-28 (server/discover)
  • pass
    protocol.statelessanswers without a session
  • pass
    protocol.transportstreamable HTTP
  • warn
    protocol.list_ttltools/list declares ttlMs 0, so clients re-fetch it on every use
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: vulnhunt_payment_resources (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); gpufeed_get_cheapest (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); gpufeed_status (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
  • pass
    tools.token_costabout 725 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

11 tools, about 725 tokens to load them all · tool set f28636b6057b · checked 2026-10-20 11:40 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 44 / 100

no-repositoryunreachable
provenance35
liveness0
freshness85
hygiene80

-unreachable(10 failures) ~updated-40d-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://vulnhunt-agent-api-production.up.railway.app/mcp streamable-httpnoneno (10 failures)76%286 ms2026-07-282026-09-28

Tools (11)

gpufeed_compare_providersCompare providers without treating missing data as unavailable.
gpufeed_estimate_trainingEstimate GPU compute cost using observed prices, with assumptions exposed.
gpufeed_get_availabilityReturn observed GPU listings from free-first sources.
gpufeed_get_cheapestReturn the cheapest verified free-first GPU offer.
gpufeed_get_historyReturn persisted verified GPU price observations.
gpufeed_get_price_indexReturn descriptive statistics over persisted GPU observations.
gpufeed_recommendReturn a bounded lowest-observed-cost recommendation for further verification.
gpufeed_statusReturn GPUFEED scope, guardrail, metering and provider status.
vulnhunt_chainsList supported chains.
vulnhunt_decisionReturn a bounded free decision packet for an EVM contract.
vulnhunt_payment_resourcesReturn the machine-readable paid resource catalog and x402 terms.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "io.github.owenkingva-web/vulnhunt",
  "title": "VulnHunt Security Intelligence",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://vulnhunt-agent-api-production.up.railway.app/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "description": "Read-only smart-contract security intelligence for autonomous agents."
}