Verdigraph is an MCP server published by io.github.jdhart81, hosted at mcp.viridisconservation.com. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 4 tools, including build_brain, verify_brain, detect_format, describe_agent.
Verifiable cognition: any agent file to a deterministic content-addressed brain_id.
134 connections through 5 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs 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.
| Parameter | Type | Description |
|---|---|---|
| format | string | verdigraph_genome, claude_project_export, openai_assistant, prompt_list or auto (default). |
| content * | string | The agent file, as a string. |
| request_id | any | Optional. Your id for this call. Repeat it to retry safely: the same request_id is never charged twice. |
| include_document | boolean | Optional. Include the full compiled document. Default false. |
{
"name": "build_brain",
"title": "Build brain",
"description": "Compile an agent file into a deterministic, content-addressed brain.\n content = the file as a string; format = verdigraph_genome |\n claude_project_export | openai_assistant | prompt_list | auto.\n Returns brain_id, content_hash, node/edge counts, the 9-invariant\n firing report, and provenance. Identical bytes always produce the\n identical brain_id (VB1). include_document=true returns the full\n graph.",
"inputSchema": {
"type": "object",
"title": "build_brainArguments",
"required": [
"content"
],
"properties": {
"format": {
"type": "string",
"title": "Format",
"default": "auto",
"description": "verdigraph_genome, claude_project_export, openai_assistant, prompt_list or auto (default)."
},
"content": {
"type": "string",
"title": "Content",
"description": "The agent file, as a string."
},
"request_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Request Id",
"default": null,
"description": "Optional. Your id for this call. Repeat it to retry safely: the same request_id is never charged twice."
},
"include_document": {
"type": "boolean",
"title": "Include Document",
"default": false,
"description": "Optional. Include the full compiled document. Default false."
}
}
},
"outputSchema": {
"type": "object",
"title": "build_brainOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
},
"annotations": {
"title": "Build brain",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}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).
| Parameter | Type | Description |
|---|---|---|
| format | string | verdigraph_genome, claude_project_export, openai_assistant, prompt_list or auto (default). |
| content * | string | The agent file, as a string. |
| brain_id | string | Optional. The claimed brain id to check. |
| content_hash | string | Optional. The claimed content hash to check. |
{
"name": "verify_brain",
"title": "Verify brain",
"description": "Machine-check a cognition claim: recompute the brain from the\n submitted content and compare against the claimed brain_id and/or\n content_hash. valid=true iff every claimed identifier matches the\n deterministic recomputation (VB3).",
"inputSchema": {
"type": "object",
"title": "verify_brainArguments",
"required": [
"content"
],
"properties": {
"format": {
"type": "string",
"title": "Format",
"default": "auto",
"description": "verdigraph_genome, claude_project_export, openai_assistant, prompt_list or auto (default)."
},
"content": {
"type": "string",
"title": "Content",
"description": "The agent file, as a string."
},
"brain_id": {
"type": "string",
"title": "Brain Id",
"default": "",
"description": "Optional. The claimed brain id to check."
},
"content_hash": {
"type": "string",
"title": "Content Hash",
"default": "",
"description": "Optional. The claimed content hash to check."
}
}
},
"outputSchema": {
"type": "object",
"title": "verify_brainOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
},
"annotations": {
"title": "Verify brain",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Detect which supported agent-file format the content is (verdigraph_genome, claude_project_export, openai_assistant, prompt_list) before building.
| Parameter | Type | Description |
|---|---|---|
| content * | string | The agent file, as a string. |
{
"name": "detect_format",
"title": "Detect format",
"description": "Detect which supported agent-file format the content is\n (verdigraph_genome, claude_project_export, openai_assistant,\n prompt_list) before building.",
"inputSchema": {
"type": "object",
"title": "detect_formatArguments",
"required": [
"content"
],
"properties": {
"content": {
"type": "string",
"title": "Content",
"description": "The agent file, as a string."
}
}
},
"outputSchema": {
"type": "object",
"title": "detect_formatOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
},
"annotations": {
"title": "Detect format",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Return capabilities and input contract.
No parameters.
{
"name": "describe_agent",
"title": "Describe this service",
"description": "Return capabilities and input contract.",
"inputSchema": {
"type": "object",
"title": "describe_agentArguments",
"properties": {}
},
"outputSchema": {
"type": "object",
"title": "describe_agentOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
},
"annotations": {
"title": "Describe this service",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Verifiable cognition for the agent economy: compile any agent file (Verdigraph genome, Claude project export, OpenAI Assistant config, prompt list) into a deterministic, content-addressed brain_id with a machine-checkable invariant report. Same bytes -> same brain, every time. Pin it in git, cite it in an audit, notarize it on the fleet.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.