Skip to content

io.github.jdhart81/verdigraph

by jdhart81 · remote · no sign-in to list tools · v0.1.0 · published by GitHub user jdhart81

Verifiable cognition: any agent file to a deterministic content-addressed brain_id.

Changes · 3
CompareRegistry entry

4 tools: 3 change things and 1 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http verdigraph https://mcp.viridisconservation.com/verdigraph/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Changes things 3Claude Code: ask
  • build_brainCompile an agent file into a deterministic, content-addressed brain.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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 bytes always produce the identical brain_id (VB1). include_document=true returns the full graph.
  • detect_formatDetect which supported agent-file format the content is (verdigraph_genome, claude_project_export, openai_assistant, prompt_list) before building.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Detect which supported agent-file format the content is (verdigraph_genome, claude_project_export, openai_assistant, prompt_list) before building.
  • verify_brainMachine-check a cognition claim: recompute the brain from the submitted content and compare against the claimed brain_id and/or content_hash.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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).
Only reads 1Claude Code: allow
  • describe_agentReturn capabilities and input contract.No findings

    Why it is in this group

    • The name "describe_agent" says "describe": a word for reading.
    Description, as the server wrote it
    Return capabilities and input contract.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http verdigraph https://mcp.viridisconservation.com/verdigraph/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__verdigraph__describe_agent"
    ],
    "ask": [
      "mcp__verdigraph__build_brain",
      "mcp__verdigraph__verify_brain",
      "mcp__verdigraph__detect_format"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as verdigraph. Review it before you use it.