Verdigraph MCP server
io.github.jdhart81/verdigraphjdhart81streamable-httpv0.1.1Scanned
Verifiable cognition: any agent file to a deterministic content-addressed brain_id.
4 tools: 3 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Verdigraph MCP server can do
The Verdigraph MCP server is published by the GitHub account jdhart81. It has 4 tools. It can create or change data (3 tools: build_brain, verify_brain and detect_format), but cannot delete data. 1 tool only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 16, 2026, version 0.1.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: Build brain
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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: Detect format
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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Verify brain
Only reads 1Show 1 read-only tool
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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Describe this service
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.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:30 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.viridisconservation.com/verdigraph/mcp: tools/list returned 4 tools to an anonymous client, including build_brain (write), verify_brain (write), detect_format (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 changed.~3 changedView diff
- Changed:build_brainChanges thingsinputSchema
- Changed:detect_formatChanges thingsinputSchema
- Changed:verify_brainChanges thingsinputSchema
Tools4 changed.~4 changedView diff
- Changed:build_brainChanges thingstitleannotations
- Changed:describe_agentOnly readstitleannotations
- Changed:detect_formatChanges thingstitleannotations
- Changed:verify_brainChanges thingstitleannotations
Install
Pinned to version 0.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http verdigraph https://mcp.viridisconservation.com/verdigraph/mcpclaude mcp add --transport http verdigraph https://mcp.viridisconservation.com/verdigraph/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .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. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as verdigraph. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.jdhart81/verdigraph/verify?hash=e2551c46c72d333fb443d53f3a1eb321230ce09dc51ffedca2cdd7fa939c416b" | jq -e '.changed == false'Pinned hash e2551c46c72d, from Nov 16, 2026, 02:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.jdhart81/verdigraph/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.jdhart81/verdigraph)Source: MCP Registry · repository. Synced Nov 16, 2026, 02:18 UTC.
Verdigraph MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Verdigraph MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Verdigraph MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Verdigraph MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Verdigraph MCP server have?
- 4 tools: 3 write, 1 read. build_brain, verify_brain, detect_format and describe_agent.
Does the Verdigraph MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Verdigraph MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Verdigraph MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.