Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "aegis-security-mcp": {
      "type": "http",
      "url": "https://bc.gensi.space/mcp"
    }
  }
}

claude mcp add --transport http aegis-security-mcp https://bc.gensi.space/mcp

[mcp_servers.aegis-security-mcp]
url = "https://bc.gensi.space/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "aegis-security-mcp": {
      "type": "remote",
      "url": "https://bc.gensi.space/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "aegis-security-mcp": {
      "type": "http",
      "url": "https://bc.gensi.space/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=aegis-security-mcp&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYmMuZ2Vuc2kuc3BhY2UvbWNwIn0%3D"
}

{
  "servers": {
    "aegis-security-mcp": {
      "type": "http",
      "url": "https://bc.gensi.space/mcp"
    }
  }
}

{
  "mcpServers": {
    "aegis-security-mcp": {
      "httpUrl": "https://bc.gensi.space/mcp"
    }
  }
}

extensions:
  "aegis-security-mcp":
    enabled: true
    name: "aegis-security-mcp"
    type: streamable_http
    uri: "https://bc.gensi.space/mcp"
    timeout: 300

Quality 73 / 100new

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 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: health (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); screen_token (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
pass
tools.token_costabout 233 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 recorded for 6 of the 7 days needed

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

2 tools, about 233 tokens to load them all · tool set 4647a0d3f59e · tools last changed 2026-10-15 · checked 2026-10-21 03:14 UTC

Tool changes

2026-10-15screen_tokenchangeddescription
before
Screen an EVM token contract for scam risk (honeypot, blacklist, high buy tax, unverified source, ownership renounced status). Use when a user asks whether a token or presale contract looks safe. Returns a structured risk summary. Data provider attribution is included (GoPlus). Idempotent, read-only, no side effects.
after · 54% of words in common
Screen an EVM token contract for scam risk (honeypot, blacklist, high buy tax, unverified source, ownership renounced status; 66-signal engine, GoPlus attribution). WHEN TO USE: user pastes a CA and asks 'is this safe / a scam / honeypot / rug?'; before a user buys, mints or claims a token; admin vets a contract before pinning. Trigger phrases: 'check this CA', 'honeypot check', 'rug check', 'safe to buy?', 'audit this contract'. NOT FOR: price predictions or trading advice. Returns a structured risk summary. Read-only, idempotent, no side effects.

Full history: list_changes · trend: quality JSON.

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 80 / 100

no-repository

provenance45

liveness100

freshness100

hygiene80

+dns-namespace +reachable +uptime-100% +updated-6d-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

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://bc.gensi.space/mcp` streamable-http	none	yes	100%	824 ms	2025-06-18	2026-10-20

Tools (2)

health Liveness probe for the Aegis security MCP server. Returns uptime and call counters.

screen_token Screen an EVM token contract for scam risk (honeypot, blacklist, high buy tax, unverified source, ownership renounced status; 66-signal engine, GoPlus attribution). WHEN TO USE: user pastes a CA and asks 'is this safe / a scam / honeypot / rug?'; before a user buys, mints or claims a token; admin vets a contract before pinning. Trigger phrases: 'check this CA', 'honeypot check', 'rug check', 'safe to buy?', 'audit this contract'. NOT FOR: price predictions or trading advice. Returns a structured risk summary. Read-only, idempotent, no side effects.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "space.gensi.bc/aegis-security-mcp",
  "_meta": {},
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://bc.gensi.space/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "description": "AI scam-shield for Web3: screen token contracts for honeypot/drain patterns. Aegis AI group admin."
}