
Anchord (AnchorID)
Provides a read-only MCP for identity resolution plus write guardrails, letting an agent resolve who an identity is while blocking unsafe writes so autonomous actions stay bounded.
About
Anchord (AnchorID) is an MCP server that offers read-only identity resolution together with write guardrails, so an AI agent can confirm who an identity is while unsafe writes are blocked. A solo builder running autonomous agents reaches for it to keep identity checks and action limits enforced at runtime. It runs as a hosted streamable-http endpoint or an npm stdio package and needs an Anchord API key.
- Read-only identity resolution
- Write guardrails for agents
- Remote streamable-http or npm stdio
- Keeps autonomous actions bounded
Anchord (AnchorID) by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --env ANCHORD_API_KEY=YOUR_ANCHORD_API_KEY --env ANCHORD_API_BASE_URL=YOUR_ANCHORD_API_BASE_URL anchord -- npx -y @anchord/mcp-serverAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | @anchord/mcp-server |
|---|---|
| Transport | STDIO, HTTP |
| Auth | Required |
What it does
Provides a read-only MCP for identity resolution plus write guardrails, letting an agent resolve who an identity is while blocking unsafe writes so autonomous actions stay bounded.
Who is it for?
Agents needing identity checks and bounded write actions
Skip if: Projects with no identity or write-safety needs