mcp-api — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited mcp-api (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Machine-readable interfaces for autonomous agents integrating with Ben Milne's published archive.
GET https://benmilne.com/mcp/v1/postsGET https://benmilne.com/mcp/v1/post/{id}GET https://benmilne.com/mcp/v1/search?query=POST https://benmilne.com/mcp (initialize, tools/list, tools/call)The MCP server exposes 3 tools via tools/list:
category and tag filters.# List tools
curl -X POST https://benmilne.com/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
# Search for posts about stablecoins
curl -X POST https://benmilne.com/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"search_posts","arguments":{"query":"stablecoin"}}}'Attribution is included in JSON envelopes. Prefer JSON for agents; use Accept: text/markdown on essay routes for prose.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.