# space.gensi.bc/aegis-security-mcp

> AI scam-shield for Web3: screen token contracts for honeypot/drain patterns. Aegis AI group admin.

- name: space.gensi.bc/aegis-security-mcp
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 80/100 flags: no-repository
- quality: 73/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/space.gensi.bc%2Faegis-security-mcp
- tools: https://api.protogrid.dev/v1/servers/space.gensi.bc%2Faegis-security-mcp/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

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


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 45
- drivers: +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.

## Quality 73/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no 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_cost`: about 233 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 6 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 2, about 233 tokens to load them all
- tool set hash: 4647a0d3f59e72487127be7ea39b3a69
- tools last changed: 2026-10-15T16:53:51.838Z
- badge: [![protogrid quality](https://protogrid.dev/badge/space.gensi.bc/aegis-security-mcp.svg)](https://protogrid.dev/servers/space.gensi.bc/aegis-security-mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-15 `screen_token` changed (description)
  - 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: 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: https://api.protogrid.dev/v1/servers/space.gensi.bc%2Faegis-security-mcp/changes

## Remotes

- https://bc.gensi.space/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## 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.