# cachly-dev/cachly-mcp

Source: https://glimind.com/server/awesome%2Fcachly-dev%2Fcachly-mcp
Registry id: `awesome/cachly-dev/cachly-mcp`
Status: unknown

## Tools (37)

- `ambient-stats`: Tokens injected vs saved — the honest net, even when negative
- `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_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`: Fill people, files and lessons from git history, incrementally
- `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`: Predict likely failures before they happen
- `brain_predict_failures`: Predict likely failures before they happen
- `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
- `causal_trace`: Root-cause analysis through the causal knowledge graph
- `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
- `health`: Check key, API, editor configs and git hook
- `learn_from_attempts`: Store a structured lesson after any fix, deploy or discovery
- `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`: The known fix for a topic, with its success and failure history
- `remember_context`: Keep architecture findings, decisions and file summaries
- `session_end`: Save what you built; extract lessons from the summary and the git log
- `session_start`: Full briefing: last session, open failures, recent lessons, Brain health
- `skill_gaps`: Knowledge blind spots: unresolved failures, missing attribution
- `smart_recall`: Hybrid BM25 + semantic + causal-graph search, 11 languages, quality-reranked
- `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

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