Is the Martinhavel Navigrants MCP server down?

mcp-registry/io.github.martinhavel/navigrants · v0.5.0

healthy
Last checked 2026-10-19 22:49 UTC · handshake 518ms

As of 2026-10-19 22:49 UTC, the Martinhavel Navigrants MCP server is up with a Glimind reliability score of 93/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 21 outages in 90 days, with a median recovery of 3 minutes.

uptime (30d checks)
100%
checks observed
3,869
outages (90d)
21
tools
6

EU Horizon Europe grant & consortium partner intelligence over 27k+ CORDIS projects, 59k orgs.

Install Martinhavel Navigrants MCP server

Add to Cursor Add to VS Code

Claude Code

claude mcp add --transport http martinhavel-navigrants-mcp-server https://app.navigrants.eu/api/mcp

Claude Desktop · Windsurf · Cline (mcpServers JSON)

{
  "mcpServers": {
    "martinhavel-navigrants-mcp-server": {
      "type": "http",
      "url": "https://app.navigrants.eu/api/mcp"
    }
  }
}

Third-party server, listed as discovered. Review its source before installing.

Agent-readiness: B (81/100)

B (81/100): 0 error(s), 3 warning(s) across 6 tool(s); ~1,112 tokens of tool definitions.
Scores higher than 36% of 15,374 MCP servers Glimind has audited.
Its tool list costs an agent ~1,112 tokens per session — lighter than 75% of servers.
81 → 81 since 2026-10-17
no tool-poisoning patterns
Schemas100
Descriptions100
Safety hints30
Token cost100
Client compatibility70
Protocol40
Reliability85
Stability100

What to fix (4)

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 →

Tools: calculate_score, find_matching_grants, find_open_calls, find_partners, get_project_detail and 1 more

Negotiates MCP 2024-11-05. Structured output, tool output schemas and elicitation arrived in 2025-06-18.

Upgrade the MCP SDK and negotiate 2025-06-18 or newer. How to fix →

Handshake + tools/list takes ~1,774 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.

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 →

Auto-fix: 6 corrected tool definitions

Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fio.github.martinhavel%2Fnavigrants/fixes

calculate_score 1 change
{
  "name": "calculate_score",
  "description": "Scores a proposed consortium against a target Horizon Europe pillar using 6 evidence-based features (V1 — max 75/100). Returns score with full factor breakdown including keyword/topic overlap.",
  "inputSchema": {
    "type": "object",
    "required": [
      "consortium_ids",
      "target_pillar"
    ],
    "properties": {
      "target_pillar": {
        "type": "string",
        "description": "Target pillar: Health, Digital, Climate, AgriFood, Energy, etc."
      },
      "consortium_ids": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Organization IDs (from find_partners or get_project_detail) in proposed consortium"
      },
      "topic_keywords": {
        "type": "string",
        "description": "Optional free-text topic keywords to refine keyword overlap scoring (e.g. \"cancer biotech\", \"machine learning safety\")"
      }
    }
  },
  "annotations": {
    "readOnlyHint": true
  }
}
find_matching_grants 1 change
{
  "name": "find_matching_grants",
  "description": "Find EU Horizon grants matching a description of your organisation or project. Returns top grants with budget, timeline, coordinator, and topic code. To score a specific consortium against any result, use calculate_score with org IDs from find_partners.",
  "inputSchema": {
    "type": "object",
    "required": [
      "description"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "default": 8,
        "description": "Max results to return (default 8, max 20)"
      },
      "pillar": {
        "type": "string",
        "description": "Narrow to a specific pillar: Health, Digital, Climate, AgriFood, Energy, Culture & Society, Excellent Science. Optional."
      },
      "description": {
        "type": "string",
        "description": "Free-text description of your organisation, technology, or project focus. E.g. 'Czech SME developing AI-assisted cancer diagnostics' or 'university research group in renewable hydrogen storage'"
      }
    }
  },
  "annotations": {
    "readOnlyHint": true
  }
}
find_open_calls 1 change
{
  "name": "find_open_calls",
  "description": "PAID. Full-text search across all currently OPEN Horizon Europe calls (future deadline — still actionable, not yet applied to). Complements search_grants, which only covers past, already-funded projects. Ranked by relevance, filterable by pillar and days-to-deadline. Requires payment via x402; call without payment first to receive the terms.",
  "inputSchema": {
    "type": "object",
    "required": [
      "topic"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "default": 10,
        "description": "Max results (default 10, max 30)"
      },
      "topic": {
        "type": "string",
        "description": "Search query (full-text) over the call title, scope and expected outcomes."
      },
      "pillar": {
        "type": "string",
        "description": "Filter by pillar: Health, Digital, Climate, AgriFood, Energy, Culture & Society, Excellent Science. Optional."
      },
      "max_days_to_deadline": {
        "type": "integer",
        "description": "Only calls whose deadline is within this many days from now. Optional."
      }
    }
  },
  "annotations": {
    "readOnlyHint": true
  }
}

Get alerted

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/io.github.martinhavel/navigrants"],"email":"[email protected]"}'

Agents: watch_tool({"toolId": "mcp-registry/io.github.martinhavel/navigrants"}) over MCP.

Passed

Largest tool definitions

Static 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:

Markdown
[![MCP agent-readiness](https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.martinhavel%2Fnavigrants.svg)](https://glimind.com/server/mcp-registry%2Fio.github.martinhavel%2Fnavigrants?ref=badge)
HTML
<a href="https://glimind.com/server/mcp-registry%2Fio.github.martinhavel%2Fnavigrants?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.martinhavel%2Fnavigrants.svg" alt="MCP agent-readiness"></a>
reStructuredText
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.martinhavel%2Fnavigrants.svg
   :target: https://glimind.com/server/mcp-registry%2Fio.github.martinhavel%2Fnavigrants?ref=badge
   :alt: MCP agent-readiness

Tool-definition log

Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:3824a00a9c9e73dc…, first seen 2026-10-17, included at leaf 14105 of 29,258. Version history · verify what your client received.

Tools (6)

Compare: most reliable ml servers · most reliable knowledge servers · most reliable search servers · most reliable data servers

Know before your agent calls it

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.

Add Glimind — free, no signup:

Add to Cursor Add to VS Code

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"
    }
  }
}

FAQ

Is the Martinhavel Navigrants MCP server down right now?

As of 2026-10-19 22:49 UTC, the Martinhavel Navigrants MCP server is up with a Glimind reliability score of 93/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 21 outages in 90 days, with a median recovery of 3 minutes.

How many tools does Martinhavel Navigrants MCP server provide?

Martinhavel Navigrants MCP server advertises 6 tools, including calculate_score, find_matching_grants, find_open_calls, find_partners, get_project_detail.

How do I install Martinhavel Navigrants MCP server?

Point your MCP client at this streamable-http endpoint: https://app.navigrants.eu/api/mcp

Is the Martinhavel Navigrants MCP server safe to connect to an AI agent?

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.

Operator of Martinhavel Navigrants MCP server?

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.

Feedback
Help us improve