Is the cachly — Explain it once. Every AI knows it. MCP server down?

mcp-registry/io.github.cachly-dev/mcp-server · v0.10.267

Also listed as awesome/cachly-dev/cachly-mcp

One MCP connection for every live tool. Your agent finds the right tool and calls it through Glimind, and skips servers that are down. Free, no signup.Add to CursorVS CodeAdd to Claude Code copies a terminal command claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server. Other clients
healthy
Last checked 2026-11-22 15:14 UTC · handshake 569ms

As of 2026-11-22 15:14 UTC, the cachly — Explain it once. Every AI knows it. MCP server is up with a Glimind reliability score of 85/100 (grade B). Over the last 30 days it answered 99.8% of Glimind's liveness checks. It had 1 outage in 90 days, with a median recovery of 9 minutes.

uptime (30d checks)
99.8%
checks observed
386
outages (90d)
1
tools
55

Keeps the rules, decisions and fixes you explain to your AI, for every session and tool. EU servers.

Point your MCP client at this streamable-http endpoint: https://mcp.cachly.dev/mcp

Agent-readiness: B (82/100)

B (82/100): 0 error(s), 2 warning(s) across 27 tool(s); ~8,351 tokens of tool definitions.
Scores higher than 28% of 27,589 MCP servers Glimind has audited.
Its tool list costs an agent ~8,351 tokens per session — more than 75% of servers.
83 → 82 since 2026-11-19
no tool-poisoning patterns
Descriptions100
Safety hints14
Schemas100
Protocol100
Stability96
Token cost100
Reliability100
Client compatibility70

What to fix (4)

27 of 27 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: autopilot, brain_doctor, brain_from_git, brain_predict, brain_search and 22 more

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 →

Tools: cache_set, roadmap_update

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 1 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: 9 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.cachly-dev%2Fmcp-server/fixes

brain_search 1 change
{
  "name": "brain_search",
  "description": "BM25+ full-text search over ALL brain data: lessons, context entries, session history, CKG nodes, roadmap items. Unlike smart_recall (which focuses on lessons + context), brain_search casts a wider net. Use when smart_recall returns nothing or when you want to find anything the brain knows about a topic.",
  "inputSchema": {
    "type": "object",
    "required": [
      "query"
    ],
    "properties": {
      "limit": {
        "type": "number",
        "description": "Max results (default: 15)"
      },
      "query": {
        "type": "string",
        "description": "What to search for"
      },
      "instance_id": {
        "type": "string",
        "description": "Brain instance ID"
      }
    }
  },
  "annotations": {
    "readOnlyHint": true
  }
}
cache_get 1 change
{
  "name": "cache_get",
  "description": "Get a value from a running cache instance by key. Returns the stored value (string or deserialized JSON object) or null if the key does not exist or has expired. Read-only — no side effects. Use cache_mget when you need multiple keys in one round-trip. Use cache_exists to check existence without retrieving the value. Use semantic_search when you need fuzzy/vector search across stored values.",
  "inputSchema": {
    "type": "object",
    "required": [
      "key"
    ],
    "properties": {
      "key": {
        "type": "string",
        "description": "Cache key to retrieve"
      },
      "org_id": {
        "type": "string",
        "description": "Optional org ID — if the direct key misses, falls back to the shared org namespace org:{org_id}:sem:{key}"
      },
      "instance_id": {
        "type": "string",
        "description": "UUID of the instance."
      }
    }
  },
  "annotations": {
    "readOnlyHint": true
  }
}
cache_set 1 change
{
  "name": "cache_set",
  "description": "Set a key-value pair in a running cache instance. Overwrites any existing value at the key — not idempotent for new data. Returns \"OK\" on success; returns an error if the instance_id is invalid or the instance is paused. Value can be a string or a JSON-serialized object. Optionally set a TTL in seconds (omit for no expiry). Use cache_mset instead for setting multiple keys in a single pipeline round-trip. Use cache_stream_set instead for caching LLM token streams (ordered string chunks).",
  "inputSchema": {
    "type": "object",
    "required": [
      "key",
      "value"
    ],
    "properties": {
      "key": {
        "type": "string",
        "description": "Cache key"
      },
      "ttl": {
        "type": "number",
        "description": "Time-to-live in seconds (optional, omit for no expiry)"
      },
      "value": {
        "type": "string",
        "description": "Value to store (string or JSON)"
      },
      "org_id": {
        "type": "string",
        "description": "Optional org ID — also writes the key to the shared org namespace org:{org_id}:sem:{key} with the same TTL"
      },
      "instance_id": {
        "type": "string",
        "description": "UUID of the cache instance (from list_instances)"
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": 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.cachly-dev/mcp-server"],"email":"[email protected]"}'

Agents: watch_tool({"toolId": "mcp-registry/io.github.cachly-dev/mcp-server"}) 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.

Badge for your README

Shows whether the server is live and its agent-readiness score; it updates within the hour.

MCP server status

Markdown
[![MCP server status](https://glimind.com/badge/mcp-registry%2Fio.github.cachly-dev%2Fmcp-server.svg)](https://glimind.com/server/mcp-registry%2Fio.github.cachly-dev%2Fmcp-server?ref=badge)
HTML
<a href="https://glimind.com/server/mcp-registry%2Fio.github.cachly-dev%2Fmcp-server?ref=badge"><img src="https://glimind.com/badge/mcp-registry%2Fio.github.cachly-dev%2Fmcp-server.svg" alt="MCP server status"></a>

Tool-definition log

Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:882555da7500e1eb…, first seen 2026-11-19, included at leaf 349273 of 384,215. Version history · verify what your client received.

Tools (55)

Compare: most reliable knowledge servers · most reliable other servers · most reliable search servers · most reliable devops servers · most reliable ml 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?ref=install-server

Claude Desktop · Windsurf · Cline (mcpServers JSON)

{
  "mcpServers": {
    "glimind": {
      "type": "http",
      "url": "https://glimind.com/mcp?ref=install-server"
    }
  }
}

FAQ

Is the cachly — Explain it once. Every AI knows it. MCP server down right now?

As of 2026-11-22 15:14 UTC, the cachly — Explain it once. Every AI knows it. MCP server is up with a Glimind reliability score of 85/100 (grade B). Over the last 30 days it answered 99.8% of Glimind's liveness checks. It had 1 outage in 90 days, with a median recovery of 9 minutes.

How many tools does cachly — Explain it once. Every AI knows it. MCP server provide?

cachly — Explain it once. Every AI knows it. MCP server advertises 55 tools, including ambient-stats, autopilot, brain_collab_pairs, brain_coverage, brain_discover.

How do I install cachly — Explain it once. Every AI knows it. MCP server?

Point your MCP client at this streamable-http endpoint: https://mcp.cachly.dev/mcp

Is the cachly — Explain it once. Every AI knows it. MCP server safe to connect to an AI agent?

Glimind scanned all 27 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 cachly — Explain it once. Every AI knows it. 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