Verdigraph is answering right now. Last checked 12 min ago. It exposes 4 tools. Last commit 1 Nov 2026.
Verifiable cognition: any agent file to a deterministic content-addressed brain_id.
We read the source, 1 d ago · tools taken from the live server · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
child = subprocess.Popen(cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE)
$("cta").innerHTML = renderCta(PAYMENT_LINK_URL);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 min ago.
claude mcp add verdigraph --transport http https://mcp.viridisconservation.com/verdigraph/mcp
https://mcp.viridisconservation.com/verdigraph/mcp
[mcp_servers.verdigraph]
url = "https://mcp.viridisconservation.com/verdigraph/mcp"
{
"mcpServers": {
"verdigraph": {
"url": "https://mcp.viridisconservation.com/verdigraph/mcp"
}
}
}
{
"servers": {
"verdigraph": {
"type": "http",
"url": "https://mcp.viridisconservation.com/verdigraph/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
build_brain
describe_agent
detect_format
verify_brain
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.viridisconservation.com/verdigraph/mcp | streamable-http | answering | 369 ms | 12 min ago |
Deterministic verification for AI coding agents: catches invented APIs and wrong calls.
Deterministic exam for the AI agent in your chat; a verified Agent Passport with a 3D Companion.
Deterministic, machine-verifiable dispute resolution for A2A escrows.
Verifiable cognition: prove a session ledger is tamper-evident; audit & import any agent's logs.
LingNao: deterministic reasoning for AI agents → verified/refuted/unverifiable. ~3ms, fail-closed.
Deterministic cross-branch conflict detection for AI coding agents
Content-addressed contracts and a verification cache that cut agent context by skipping proven code.
Verifiable memory for AI assistants: typed facts, content-addressed versions and an audit trail.
Answers built from our own checks of this server.