Is the Raccha MCP server down?

mcp-registry/ai.raccha/raccha · v3.2.0

healthy
Last checked 2026-10-22 15:08 UTC · handshake 169ms

As of 2026-10-22 15:08 UTC, the Raccha MCP server is up with a Glimind reliability score of 83/100 (grade B). Over the last 30 days it answered 99.7% of Glimind's liveness checks. It had 21 outages in 90 days, with a median recovery of 9 minutes.

uptime (30d checks)
99.7%
checks observed
4,246
outages (90d)
21
tools
67

MCP-first toolbox for agents: KV storage, auth, queue, and utility tools. Free in early access.

Install Raccha MCP server

Add to Cursor Add to VS Code

Claude Code

claude mcp add --transport http raccha-mcp-server https://raccha.ai/mcp

Claude Desktop · Windsurf · Cline (mcpServers JSON)

{
  "mcpServers": {
    "raccha-mcp-server": {
      "type": "http",
      "url": "https://raccha.ai/mcp"
    }
  }
}

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

Agent-readiness: D (65/100)

D (65/100): 0 error(s), 5 warning(s) across 67 tool(s); ~14,194 tokens of tool definitions.
Scores higher than 1% of 15,544 MCP servers Glimind has audited.
Its tool list costs an agent ~14,194 tokens per session — more than 85% of servers.
57 → 65 since 2026-10-17
no tool-poisoning patterns
Schemas86
Descriptions54
Safety hints1
Token cost75
Client compatibility70
Protocol100
Reliability100
Stability84

What to fix (7)

67 of 67 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: cert_inspect, create_access_key, create_org, create_role, delete_role and 62 more

67 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. How to fix →

77 parameter(s) across 34 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. How to fix →

Tools: create_access_key, create_role, discussion_claim_role, discussion_create, discussion_get and 29 more

16 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 →

Tools: create_access_key, create_org, create_role, delete_role, discussion_create and 11 more

6 tool(s) have parameters with no type (no type/enum/anyOf/$ref).

Give every parameter a "type" (or "enum"/"anyOf"). Untyped parameters make models guess — strings for numbers, objects for arrays. How to fix →

Tools: kv_cas, kv_put, kv_put_ttl, queue_push, queue_push_delayed and 1 more

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 →

In the last 30 days: 0 tool(s) removed and 4 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. How to fix →

Auto-fix: 42 corrected tool definitions

Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 34 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fai.raccha%2Fraccha/fixes

create_access_key 1 change
{
  "name": "create_access_key",
  "description": "Create a scoped, revocable access_key bound to a role. Requires an admin owner_key. The raw key (`ak_...` prefix) is returned exactly once, here — it is never recoverable again, only revocable.",
  "inputSchema": {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "label"
    ],
    "properties": {
      "label": {
        "type": "string"
      },
      "expiry": {
        "type": [
          "string",
          "null"
        ],
        "default": null,
        "description": "RFC3339 expiry, e.g. \"2026-12-31T00:00:00Z\"."
      },
      "role_ids": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "default": [],
        "description": "Roles to bind this key to (combination, bundle-26). Unset/empty grants no scopes (denies everything)."
      },
      "owner_key": {
        "type": [
          "string",
          "null"
        ],
        "default": null,
        "description": "Owner key. Must belong to an admin member.\nOptional. If omitted, defaults to the owner_key resolved from the\nconnection's `Authorization: Bearer <owner_key>` header."
      },
      "mailbox_label": {
        "type": "string",
        "default": ""
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false
  }
}
create_org 1 change
{
  "name": "create_org",
  "description": "Create a new, deliberately-named org under the same email as the supplied owner_key — not a fresh signup. `name` is slugified into the org's namespace slug (e.g. \"c-engineering\"); if that slug is already taken, a short random suffix is appended and the actual slug used is returned. Subject to the same per-email account-creation quota as signup. Returns a fresh owner_key in the same shape as `switch_org`.",
  "inputSchema": {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "name"
    ],
    "properties": {
      "name": {
        "type": "string",
        "description": "Human-readable name for the new org, e.g. \"c-engineering\". Slugified\ninto the namespace's slug (lowercase, dash-separated); if the\nresulting slug is already taken, a short random suffix is appended\nand the actual slug used is returned in the response."
      },
      "owner_key": {
        "type": [
          "string",
          "null"
        ],
        "default": null,
        "description": "Any valid owner_key for this email. The new org is created under the\nsame email, not a fresh signup.\nOptional. If omitted, defaults to the owner_key resolved from the\nconnection's `Authorization: Bearer <owner_key>` header."
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false
  }
}
create_role 1 change
{
  "name": "create_role",
  "description": "Create a role: a named, reusable set of scope_expressions that an access_key can be bound to. Requires an admin owner_key — access_keys can never call this.",
  "inputSchema": {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "name"
    ],
    "properties": {
      "name": {
        "type": "string"
      },
      "owner_key": {
        "type": [
          "string",
          "null"
        ],
        "default": null,
        "description": "Owner key. Must belong to an admin member — access_keys can never call this.\nOptional. If omitted, defaults to the owner_key resolved from the\nconnection's `Authorization: Bearer <owner_key>` header."
      },
      "scope_expressions": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "default": [],
        "description": "Scope expressions in `<structure>:<prefix>` form, e.g. \"kv.get:billing.acme.*\"."
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false
  }
}

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/ai.raccha/raccha"],"email":"[email protected]"}'

Agents: watch_tool({"toolId": "mcp-registry/ai.raccha/raccha"}) 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%2Fai.raccha%2Fraccha.svg)](https://glimind.com/server/mcp-registry%2Fai.raccha%2Fraccha?ref=badge)
HTML
<a href="https://glimind.com/server/mcp-registry%2Fai.raccha%2Fraccha?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fai.raccha%2Fraccha.svg" alt="MCP agent-readiness"></a>
reStructuredText
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fai.raccha%2Fraccha.svg
   :target: https://glimind.com/server/mcp-registry%2Fai.raccha%2Fraccha?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 sha256:73f2f9fb45bb34ad…, first seen 2026-10-17, included at leaf 6471 of 46,630. Version history · verify what your client received.

Tools (67)

Compare: most reliable security servers · most reliable other servers · most reliable communication servers · most reliable data servers · most reliable email 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 Raccha MCP server down right now?

As of 2026-10-22 15:08 UTC, the Raccha MCP server is up with a Glimind reliability score of 83/100 (grade B). Over the last 30 days it answered 99.7% of Glimind's liveness checks. It had 21 outages in 90 days, with a median recovery of 9 minutes.

How many tools does Raccha MCP server provide?

Raccha MCP server advertises 67 tools, including cert_inspect, create_access_key, create_org, create_role, delete_role.

How do I install Raccha MCP server?

Point your MCP client at this streamable-http endpoint: https://raccha.ai/mcp

Is the Raccha MCP server safe to connect to an AI agent?

Glimind scanned all 67 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 Raccha 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