Umtri MCP server
online · 100% uptimeio.umtri/umtri·v1.5.3Give your AI agent a persistent map of your project's structure, dependencies, and bugs.
0 stars135 downloads/wk
Reviews
Write oneNobody has reviewed Umtri yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Umtri tools
Tool list not cached yet. `describe` through the gateway fetches it live.
Public scan report
scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it
- Code scan7 source files scanned25/25
- Live reliabilityremote reachable in 1115ms (auth required)20/20
- –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
- Auth qualityauth enforced (unknown)9/15
- Maintenancelast push 31 days ago12/15
- Maintainer identityendpoint served from the registry-verified namespace domain8/10
How Umtri compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 87/100
- higher than 78% of 4,460 AI and agents servers
- Uptime
- 100%
- of our recent checks; the typical remote AI and agents server answers 100%
- Response time
- 708 ms
- faster than 17% of 2,331 AI and agents servers
- Downloads a week
- 135
- more than 69% of 1,538 AI and agents servers with a package
Release history: 8 versions in the registry since 2026-07-31, latest 2026-10-03, typically one every 1 day.
Install Umtri in Claude Code, Cursor or VS Code
claude mcp add --transport http umtri https://mcp.umtri.io
What the publisher says
From the Umtri repository's README, as published. We do not edit it. Read it on GitHub
umtri-mcp
MCP server for Umtri — give your AI coding agent a persistent map of your project's structure, dependencies, and bugs.
Your agent re-derives your codebase from scratch every session. Umtri stores the structure once and hands it back through MCP: a tree of what the system is made of, the calls and dependencies between its parts, and the bugs eroding it. Ask "what breaks if I change this?" and get an answer traced through recorded connections rather than guessed from a grep.
Quick start
The fastest path is the hosted endpoint at https://mcp.umtri.io — nothing to install. Generate a token at app.umtri.io → Settings → API Tokens, then:
claude mcp add --transport http umtri https://mcp.umtri.io \
--header "Authorization: Bearer umtri_pat_xxxxxxxxxxxxxxxx"Any MCP client that takes a config object uses the same shape:
{
"mcpServers": {
"umtri": {
"type": "http",
"url": "https://mcp.umtri.io",
"headers": { "Authorization": "Bearer umtri_pat_xxxxxxxxxxxxxxxx" }
}
}
}Run it yourself (stdio)
Use this package when you want to pin a version or point at a self-hosted API:
claude mcp add umtri \
-e UMTRI_API_TOKEN=umtri_pat_xxxxxxxxxxxxxxxx \
--transport stdio \
-- npx -y umtri-mcpThe token is not validated at setup time, so a bad token connects but every call fails. If tools appear and then error, re-check the token and its scope — read tokens cannot call any write tool.
Tools
Read — getgraph, getbug, getimpact, listprojects, listbugs, listseasons, list_events
Write — createproject, createnode, updatenode, deletenode, createedge, deleteedge, createapi, updateapi, deleteapi, createbug, updatebug, deletebug
Plan loop — commitplan, recordcommit, reopen_transplant
get_graph returns a slice, not a dump: scope by subtree (rootId), by layer (maxType), by role, or by season, and control description weight separately. A large tree stays cheap to read.
Resources
Seven read-only documents the agent can pull for domain rules — the plant vocabulary (trunk/limb/twig/leaf/vein), what counts as a node and what does not, how seasons work, how plan nodes are meant to be realized, and how a ground behaves while transplanting.
umtri://rules/vocabulary umtri://rules/transplant
umtri://rules/vocabulary-detailed umtri://rules/plan
umtri://rules/seasons umtri://about/vision
umtri://rules/system-structureLinks
- Docs —
- App —
- Site —
License
Apache-2.0. See LICENSE.
Nothing above is checked by us. What we check is on the safety report.
Umtri: common questions
- Is Umtri MCP server safe?
- Yes, by our scan: it is graded A (87/100). Read the Umtri safety report
- How do I install Umtri?
- It runs remotely at mcp.umtri.io. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Umtri need an API key?
- Yes. The registry entry asks for
UMTRI_API_TOKEN. - Is Umtri maintained?
- The last commit was 32 days ago (2026-10-03). The latest release is v1.5.3.
- Is Umtri up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- What can I use instead of Umtri?
- Servers from other publishers that do the same job: Figma Context MCP server, Memanto MCP server and World Model MCP server.
- How does Umtri compare with other AI and agents MCP servers?
- safety score 87/100 (higher than 78% of 4,460 AI and agents servers); uptime 100% (of our recent checks; the typical remote AI and agents server answers 100%); response time 708 ms (faster than 17% of 2,331 AI and agents servers). Full comparison.
Alternatives to Umtri
Same job from other publishers: the closest match first, then the best rated.
- Figma ContextGive your coding agent access to your Figma data. Implement designs in any framework in one-shot.not reviewedWidely usedB
- MemantoMCP server for Memanto - persistent semantic memory for any MCP-compatible agentnot reviewedEstablishedA
World Model MCPPersistent 3D/2D spatial world model for AI agents with dynamic velocity and entity tracking.not reviewedEstablishedA- Total Agent MemoryPersistent local memory for coding agents: temporal knowledge graph, procedural and episodic recallnot reviewedEstablishedA
- 3D AI Agent Avatar3D AI Agent Avatar — render any GLB, give it a Solana wallet, a voice, and pump.fun powers.not reviewedEstablishedB