mcp-registry/mu.micro/mu · v1.0.0
Also listed as glama/micro/mu
As of 2026-10-17 06:05 UTC, the Micro Mu MCP server is up with a Glimind reliability score of 92/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 74 outages in 90 days, with a median recovery of 3 minutes.
News, web search, mail, markets, weather, places, files, calendar, contacts. 67 tools, one endpoint.
Claude Code
claude mcp add --transport http micro-mu-mcp-server https://micro.mu/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"micro-mu-mcp-server": {
"type": "http",
"url": "https://micro.mu/mcp"
}
}
}
Third-party server, listed as discovered. Review its source before installing.
167 tools on one server. Tool-selection accuracy drops as the menu grows, and some clients (e.g. Cursor) cap the number of active tools.
Group tools by task into smaller servers or toolsets, and merge near-duplicates behind one tool with a mode parameter.
30 parameter(s) across 18 tool(s) have no description.
Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call.
18 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads.
1 tool(s) have descriptions under 20 characters.
Say when to use the tool and what it returns, not just its name restated ("Get weather" → "Current weather for a city: temperature, conditions, wind. Use for 'now', not forecasts.").
Loading this server's tool list costs an agent ~19,343 tokens before any work — more than 95% of MCP servers.
Split rarely-used tools into a separate server or a toolset the client can enable, or expose one "search tools" entry point. Many agents load every connected server's tools into every request.
Negotiates MCP 2025-03-26. Structured output, tool output schemas and elicitation arrived in 2025-06-18.
Upgrade the MCP SDK and negotiate 2025-06-18 or newer.
Handshake + tools/list takes ~1,879 ms.
Serve tools/list from memory, keep the process warm, and host close to your users. Every new agent session pays this before its first call.
In the last 30 days: 10 tool(s) removed and 6 schema change(s).
Add new tools or optional parameters instead of renaming or removing; deprecate first (say so in the description) and remove later. Agents cache tool contracts.
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably.
88 of 167 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones.
6 tools share an identical description with another tool on this server.
Make each description say how the tool differs from its siblings, or the model will pick between them at random.
Runs commands or code supplied by the model. Legitimate for dev tools; clients should require confirmation. Example (shell_run, name): "shell_run(dir, command, timeout)"
Declare destructiveHint/readOnlyHint on these tools and say plainly in the description what runs, where, and with what limits.
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 18 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fmu.micro%2Fmu/fixes
{
"name": "apps_create",
"description": "Create an app — a small, self-contained HTML tool hosted here. Takes the HTML; apps_build writes it for you from a description Apps run in a sandbox. Use fetch('/api/v1/<service>/<method>') or mu.service(name, method, args); mu.api does not exist. Direct external fetch is blocked. Inspect real service schemas and data before coding; never invent fields, rankings or claim runtime verification from static checks.",
"inputSchema": {
"type": "object",
"required": [
"name",
"html"
],
"properties": {
"html": {
"type": "string",
"description": "The app's HTML, inline CSS and JavaScript included, up to 256KB"
},
"icon": {
"type": "string",
"description": "An SVG icon"
},
"name": {
"type": "string",
"description": "App name, e.g. \"Pomodoro Timer\""
},
"slug": {
"type": "string",
"description": "URL-friendly id, e.g. pomodoro-timer. Derived from the name if omitted"
},
"tags": {
"type": "string",
"description": "Comma-separated tags"
},
"price": {
"type": "number",
"description": "Credits charged per use, 0 for free, up to 1000"
},
"public": {
"type": "boolean",
"description": "Publish only when explicitly requested by the owner. Personal apps are private by default."
},
"private": {
"type": "boolean",
"description": "Keep this app private to its owner; use true for personal widgets"
},
"description": {
"type": "string",
"description": "What the app does. Defaults to the name"
}
}
},
"annotations": {
"title": "Create apps",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
},
"title": "Create apps"
}{
"name": "blog_create",
"description": "Publish a post to the caller's blog. For anything meant to be read later by other people — notes, write-ups, announcements. For a private note to yourself, prefer files or memory",
"inputSchema": {
"type": "object",
"required": [
"content"
],
"properties": {
"tags": {
"type": "string",
"description": "Comma-separated tags"
},
"title": {
"type": "string",
"description": "Post title. One is generated from the body if omitted"
},
"content": {
"type": "string",
"description": "The post body, at least 50 characters"
},
"private": {
"type": "boolean",
"description": "True to keep it to yourself"
}
}
},
"annotations": {
"title": "Create blog",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
},
"title": "Create blog"
}{
"name": "blog_update",
"description": "Edit one of the caller's own posts. Fields left out keep their current value",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "The post's id, as given by blog_list"
},
"tags": {
"type": "string",
"description": "New comma-separated tags. Left alone if omitted"
},
"title": {
"type": "string",
"description": "New title. Left alone if omitted"
},
"content": {
"type": "string",
"description": "New body, at least 50 characters. Left alone if omitted"
}
}
},
"annotations": {
"title": "Update blog",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": true
},
"title": "Update blog"
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/mu.micro/mu"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/mu.micro/mu"}) over MCP.
apps_create ~378 tokensroutes_eta ~341 tokensevents_create ~318 tokensroutes_directions ~316 tokensapps_edit ~307 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live. Embed the readiness badge:
[](https://glimind.com/server/mcp-registry%2Fmu.micro%2Fmu?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fmu.micro%2Fmu?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fmu.micro%2Fmu.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fmu.micro%2Fmu.svg :target: https://glimind.com/server/mcp-registry%2Fmu.micro%2Fmu?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:12fd6e584baa0d56…, first seen 2026-10-17, included at leaf 99 of 17,012. Version history · verify what your client received.
Compare: most reliable productivity servers · most reliable devops servers · most reliable code servers · most reliable web servers · most reliable search servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp"
}
}
}
As of 2026-10-17 06:05 UTC, the Micro Mu MCP server is up with a Glimind reliability score of 92/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 74 outages in 90 days, with a median recovery of 3 minutes.
Micro Mu MCP server advertises 167 tools, including apps_build, apps_builds, apps_buildstatus, apps_collection, apps_create.
Point your MCP client at this streamable-http endpoint: https://micro.mu/mcp
Glimind scanned all 167 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.