All servers · AI models & agents

io.github.jdhart81/verdigraph

io.github.jdhart81/verdigraph · v0.1.0

No registry update 90+ days

Measured by MCP Station

Last check	Reachable
Checked at	—
Check success 7 / 30 days	—
First-try success 30 days	—
Median response	—
Lookups 30 days	—
Authentication	No auth
MCP version	2025-06-18
Rank score	—
Declared risk	Not declared (tools carry no read/destructive hints)
Capabilities declared	experimental, prompts, resources, tools
Tool definitions	4 tools · with description 100% · input schema is an object 100% · read/destructive hints 0%

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

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

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

{
  "mcpServers": {
    "verdigraph": {
      "url": "https://mcp.viridisconservation.com/verdigraph/mcp"
    }
  }
}

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.

Repository · JSON · Text for agents · Registry updated 2026-07-18