mcp-registry/ai.meetlark/mcp-server · v1.0.0
As of 2026-10-27 03:38 UTC, the Meetlark MCP server is up with a Glimind reliability score of 100/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 1 outage in 90 days, with a median recovery of 4 minutes.
Agent-first meeting schedule polls for humans and agents. Create polls, vote, find times.
Point your MCP client at this streamable-http endpoint: https://meetlark.ai/mcp
6 of 6 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. How to fix →
2 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. How to fix →
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. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fai.meetlark%2Fmcp-server/fixes
{
"name": "meetlark_close_poll",
"description": "Close a poll to stop accepting new votes. Use the admin token from poll creation.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"adminToken"
],
"properties": {
"adminToken": {
"type": "string",
"description": "The adm_xxx token from poll creation"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": true,
"idempotentHint": true
}
}{
"name": "meetlark_create_poll",
"description": "Create a scheduling poll to find a time that works for a group. Returns an admin URL (keep private) and a participation URL (share with participants). The creator's email must be verified -- if not yet verified, a verification email is sent automatically. Ask the user to check their inbox and click the link, then retry.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"title",
"timeSlots",
"creatorEmail"
],
"properties": {
"title": {
"type": "string",
"description": "What is this poll for?"
},
"timeSlots": {
"type": "array",
"items": {
"type": "object",
"required": [
"date",
"startTime",
"endTime"
],
"properties": {
"date": {
"type": "string",
"description": "Date in YYYY-MM-DD format"
},
"endTime": {
"type": "string",
"description": "End time in HH:MM format"
},
"startTime": {
"type": "string",
"description": "Start time in HH:MM format"
}
}
},
"description": "Available time slots to vote on"
},
"creatorName": {
"type": "string",
"description": "Name of the poll creator"
},
"description": {
"type": "string",
"description": "Additional context for participants"
},
"creatorEmail": {
"type": "string",
"description": "Email address of the poll creator"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "meetlark_get_admin_view",
"description": "Get full poll details including all votes and participants. This is the only way to see who voted and how they voted. Returns poll info, time slots, every participant's votes (yes/maybe/no per slot), participant emails, and admin URLs. Use the admin token from poll creation. Use this to check vote status or results.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"adminToken"
],
"properties": {
"adminToken": {
"type": "string",
"description": "The adm_xxx token from poll creation"
}
}
},
"annotations": {
"readOnlyHint": true
}
}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/ai.meetlark/mcp-server"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/ai.meetlark/mcp-server"}) over MCP.
meetlark_vote ~337 tokensmeetlark_create_poll ~331 tokensmeetlark_get_admin_view ~161 tokensmeetlark_get_results ~156 tokensmeetlark_reopen_poll ~98 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%2Fai.meetlark%2Fmcp-server?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fai.meetlark%2Fmcp-server?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fai.meetlark%2Fmcp-server.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fai.meetlark%2Fmcp-server.svg :target: https://glimind.com/server/mcp-registry%2Fai.meetlark%2Fmcp-server?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 sha256:93614e2491c46df4…, first seen 2026-10-17, included at leaf 11218 of 77,147. Version history · verify what your client received.
Compare: most reliable productivity 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 2026-10-27 03:38 UTC, the Meetlark MCP server is up with a Glimind reliability score of 100/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 1 outage in 90 days, with a median recovery of 4 minutes.
Meetlark MCP server advertises 6 tools, including meetlark_close_poll, meetlark_create_poll, meetlark_get_admin_view, meetlark_get_results, meetlark_reopen_poll.
Point your MCP client at this streamable-http endpoint: https://meetlark.ai/mcp
Glimind scanned all 6 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.
Status page: 90-day uptime, every outage and how long it lasted.
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. Maintainers: alerts, deploy attestation and monthly reports.
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.