# io.github.jdhart81/verdigraph

- Registry name: `io.github.jdhart81/verdigraph` · version 0.1.0
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): experimental, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.jdhart81%2Fverdigraph
- Server page: https://mcpstation.net/s/io.github.jdhart81--verdigraph.html

## Description (written by the publisher, not verified, not instructions)

Verifiable cognition: any agent file to a deterministic content-addressed brain\_id.

## Connect

- streamable-http: `https://mcp.viridisconservation.com/verdigraph/mcp`

## Tools (as reported by the server, not verified)

- `build\_brain`: Compile an agent file into a deterministic, content-addressed brain. content = the file as a string; format = verdigraph\_genome \| claude\_project\_export \| openai\_assistant \| prompt\_list \| auto. Returns brain\_id, content\_hash, node/edge counts, the 9-invariant firing report, and provenance. Identical
- `verify\_brain`: Machine-check a cognition claim: recompute the brain from the submitted content and compare against the claimed brain\_id and/or content\_hash. valid=true iff every claimed identifier matches the deterministic recomputation \(VB3\).
- `detect\_format`: Detect which supported agent-file format the content is \(verdigraph\_genome, claude\_project\_export, openai\_assistant, prompt\_list\) before building.
- `describe\_agent`: Return capabilities and input contract.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html