# Cachly Dev MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.cachly-dev%2Fmcp-server
Registry id: `mcp-registry/io.github.cachly-dev/mcp-server`
Status: live (checked 2026-11-22T15:14:09.886Z)

## Measurements (30 days)

- Uptime: 99.78%
- Checks: 386
- Outages (90 days): 1

## Install

```json
{
  "mcpServers": {
    "cachly-dev-mcp-server": {
      "type": "http",
      "url": "https://mcp.cachly.dev/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http cachly-dev-mcp-server https://mcp.cachly.dev/mcp
```

## Tools (55)

- `ambient-stats`: Tokens injected vs saved — the honest net, even when negative
- `autopilot`: Generate a CLAUDE.md / copilot-instructions.md that makes any AI self-managing forever. Writes a configuration file to disk — will overwrite an existing file at
- `brain_collab_pairs`: Who works with whom, with bus-factor alerts
- `brain_coverage`: A 0–100 health score for the knowledge of your codebase
- `brain_discover`: Search the Brain marketplace for ready-made knowledge bases
- `brain_doctor`: Check the health of your AI Brain and get actionable recommendations. Reports: lesson count, context entries, last session age, open failures, quality score, ef
- `brain_file_map`: Experts and lessons per file, before you touch it
- `brain_from_ci`: Bulk-ingest CI outcomes: red→green becomes a fix lesson with a causal fixes edge
- `brain_from_git`: Bootstrap brain lessons from git history. Parses commit messages and infers fix/feature/refactor lessons automatically. Great for onboarding an existing codebas
- `brain_import`: Import a shared Brain into yours
- `brain_portability`: Config snippets for 7 MCP clients, so the same Brain serves any model
- `brain_predict`: READ-ONLY — no side effects, no writes, no external network calls. Predictive Pre-fetch Engine (PPE): given your current context, reads the CKG in your Redis in
- `brain_predict_failures`: Predict likely failures before they happen
- `brain_search`: BM25+ full-text search over ALL brain data: lessons, context entries, session history, CKG nodes, roadmap items. Unlike smart_recall (which focuses on lessons +
- `brain_seed_starter`: Seed 16 universal lessons so your first smart_recall finds something
- `brain_share`: Publish a Brain snapshot as a link (public or unlisted)
- `brain_share_list`: List your shares
- `brain_unshare`: Revoke a share so the link goes dead
- `brain_who_knows`: Find your team's experts on a topic, ranked from authorship
- `cache_get`: 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
- `cache_set`: 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 er
- `cachly_tool`: Run any of cachly's specialist tools by name. The most-used tools are listed separately above. This one reaches the other 98 without their schemas taking up roo
- `causal_trace`: Root Cause Analysis through memory: given a problem description, traces the causal chain from root cause through intermediate failures to the current symptom, t
- `ckg_inspect`: Inspect the causal graph around a concept
- `compact_recover`: Recover your context after you hit the context-window limit
- `digest`: What your Brain learned this week, shareable
- `doctor`: Diagnose a broken or missing install, with the fix for each step
- `forget_context`: Delete one or more cached context entries. Use when context is stale or you want to force a fresh analysis. Supports glob patterns: "file:*" deletes all file su
- `health`: Check key, API, editor configs and git hook
- `index_project`: Index local source files into the cachly semantic cache so AI assistants can use semantic_search to find relevant files instead of re-reading the whole codebase
- `learn_from_attempts`: Store a lesson AFTER any non-trivial task (deploy, debug, fix, decision); future sessions recall it. instance_id may be omitted (never guess one). If the topic 
- `list_remembered`: List all cached context entries for this project. Shows what knowledge the AI assistant has already cached, so you can decide whether to recall existing context
- `madc_deliberate`: Specialist AI agents vote to resolve contradictory lessons
- `memory_consolidate`: Detect contradictions, merge duplicates, expire stale lessons
- `memory_crystalize`: Distill all lessons into a Crystal for instant team context
- `recall_best_solution`: Recall the best known solution for a topic from past lessons. Call this BEFORE attempting any task that might have been done before. Returns the most recent suc
- `recall_context`: Retrieve previously saved context from the cache. Returns the saved content or null if not found. Use this at the START of any task to check if you already have
- `remember_context`: Save context information to the cache so you can recall it later without re-computing. Perfect for caching: codebase overviews, file summaries, project structur
- `roadmap_add`: Add a new item to the persistent project roadmap stored in the Brain. Items survive across sessions and editors — the roadmap is always up to date. Use for feat
- `roadmap_list`: List all roadmap items, optionally filtered by status, priority, tag, or milestone. Returns items sorted by priority then creation date. Called automatically by
- `roadmap_next`: Get the single most important next actionable roadmap item. Returns the highest-priority in-progress item first, then planned items, sorted by priority. Call at
- `roadmap_update`: Update the status, priority, or details of a roadmap item. Use to move items through the lifecycle: planned → in-progress → done (or blocked/cancelled). Also us
- `semantic_search`: Find cached entries that are semantically similar to a natural-language query. Read-only — no side effects. Returns an array of objects, each with: key, value, 
- `session_end`: Save a session summary when you finish working. Records what was accomplished, files changed, and lesson count. The next session_start will show this summary as
- `session_handoff`: Save a detailed handoff for the NEXT chat window / session. Stores: current progress, TODO list (done + remaining), changed files with descriptions, instruction
- `session_start`: Single-call session briefing for the START of a session: last summary, recent lessons, health. It does not replace smart_recall for a concrete task. Returns: la
- `skill_gaps`: Knowledge blind spots: unresolved failures, missing attribution
- `smart_recall`: Returns the fixes, decisions and pitfalls this team already learned for the task at hand. Call it FIRST at the start of every coding task — before reading files
- `status`: Lessons, recalls and team at a glance
- `team_audit`: Admin-only governance trail: every role change and lesson confirmation
- `team_confirm`: A reviewer confirms a lesson; confirmed lessons rank higher in recall
- `team_crystallize`: A Team Crystal: fixes that 2 or more teammates reached independently
- `team_expertise_map`: The team's skills matrix in one table
- `team_learn`: Store a lesson in a shared team brain so all team members benefit. Like learn_from_attempts, but REQUIRES an author name for attribution. Shows up in team_recal
- `team_recall`: Recall lessons from a shared team brain, showing who learned what. Works on any shared instance (all team members using the same instance_id). Shows author, rec

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
