mcp-server

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 the target path. No auth required beyond a valid instance_id. The generated file instructs Claude, Cursor, Copilot, Windsurf, or Gemini to automatically call session_start at window open, learn_from_attempts after every fix, and session_end before closing — without being asked. Returns the generated file content as a string and the path where it was written. Use style="minimal" for just the three hooks; style="full" for the complete ruleset with examples. One command. Every AI. Always on. Use setup_ai_memory instead if you want an interactive one-shot setup that also creates an instance.

Check the health of your AI Brain and get actionable recommendations. Reports: lesson count, context entries, last session age, open failures, quality score, effective IQ boost, stale index. Returns a prioritized list of issues with fix instructions.

Bootstrap brain lessons from git history. Parses commit messages and infers fix/feature/refactor lessons automatically. Great for onboarding an existing codebase — run once and the brain instantly knows your team's accumulated patterns. Incremental by default: only processes new commits since the last run, so repeated calls are fast. Emits progress updates to stderr during long scans.

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 instance to predict likely failures and return the highest-confidence fixes. "Pre-load" means results are returned inline — nothing is cached or persisted. Requires a valid instance_id (your Redis brain). No rate limits. Call at session start when working on a specific feature or debugging area. Set scope="org" to widen prediction across your whole organisation — surfaces cross-team risks ("failed 3× across 2 other teams") from the Org Knowledge Graph, so an incident in one team becomes a vaccine for yours.

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.

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.

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).

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 room in every request. When: compact_recover (after a context limit); brain_predict_failures (before a risky step, with odds); brain_plan (plan a task from past lessons); brain_conflicts (lessons contradict); memory_crystalize (condense lessons). Unsure about a tool's arguments? Call it with describe:true first — that returns its input schema instead of running it. Available: list_instances, create_instance, get_instance, get_connection_string, delete_instance, cache_delete, cache_exists, cache_ttl, cache_keys, cache_stats, detect_namespace, cache_warmup, cache_mset, cache_mget, cache_lock_acquire, cache_lock_release, get_api_status, recall_feedback, lesson_verified, session_start_summary, session_ping, auto_learn_session, brain_who_knows, brain_file_map, team_expertise_map, brain_collab_pairs, brain_portability, skill_gaps, brain_coverage, brain_metrics, brain_changelog, brain_service_map, sync_file_changes, team_confirm, team_assign_role, team_whoami, team_roster, team_audit, team_grant_scope, team_scopes, team_synthesize, memory_crystalize, team_crystallize, brain_hygiene, global_learn, global_recall, publish_lesson, import_public_brain, recall_at, trace_dependency, list_orgs, create_org, invite_member, get_org_plan, setup_ai_memory, cache_stream_set, cache_stream_get, cache_org_stats, set_cost_per_call, memory_consolidate, brain_diff, knowledge_decay, syndicate, syndicate_search, syndicate_stats, syndicate_trending, brain_marketplace, brain_install, ckg_inspect, brain_plan, brain_conflicts, brain_resolve_conflict, brain_confirm_ci, brain_briefing, brain_contribute_signal, brain_import_meta, madc_deliberate, cls_ingest, cls_install_hooks, fedbrain_contribute, fedbrain_search, fedbrain_confirm, fedbrain_status, brain_federate, crystal_view, compact_recover, brain_from_ci, brain_watch, brain_predict_failures, brain_share, brain_import, brain_share_list, brain_unshare, brain_discover, brain_seed_starter, brain_graph, brain_set_pref, brain_get_pref

Root Cause Analysis through memory: given a problem description, traces the causal chain from root cause through intermediate failures to the current symptom, then surfaces the exact solution that worked before. Read-only — does not modify any stored data. Requires prior learning: brain must have lessons stored via learn_from_attempts or brain_from_git. Returns an ordered chain of concepts with confidence scores plus the matching solution; returns an empty chain with a message if no causal path is found. Example: causal_trace(problem="auth breaks after restart") → "Root: k8s:namespace-terminating → keycloak:jwks-race → Solution: PollUntilContextTimeout 3min". Use recall_best_solution for direct topic lookup, syndicate_search for community patterns, and causal_trace when you have a symptom and need the full root-cause chain.

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 summaries.

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 every time. Walks a directory recursively, reads each matching file, and stores a summary + path as a semantic cache entry (prompt = file path + content excerpt, value = relative path). Requires an embedding provider (OPENAI_API_KEY or CACHLY_EMBED_PROVIDER + key). Run once, then re-run after major refactors. TTL=86400 (24h) keeps entries fresh.

Store a lesson AFTER any non-trivial task (deploy, debug, fix, decision); future sessions recall it. instance_id may be omitted; the configured instance is used — never guess one. If the topic already exists, the write is an UPDATE and REQUIRES `grund` (one line: WHY the previous version was wrong) — without it the update is rejected. A conflicting outcome triggers a contradiction warning. Example: learn_from_attempts(topic="deploy:api", outcome="success", what_worked="PORT 3095 SERVES WHISPER — nohup docker compose up -d", severity="critical")

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 or refresh it. Returns: key, category, size, TTL remaining, and a content preview.

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 successful lesson for the topic, with confidence indicator. ⚠️ badge = lesson is >5d old (verify before applying). 🔴 = >10d old (likely stale!). Recalling a lesson resets its confidence clock to 1.0 (marks as recently verified). A superseded lesson shows a banner naming its successor; if the successor was deleted, the banner says so and the lesson counts as the best remaining answer. Example: recall_best_solution(topic="deploy:web") → returns the working deploy command.

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 relevant context cached, before doing expensive operations like reading many files. Supports glob patterns: "file:*" matches all file summaries, "arch*" matches architecture-related keys.

Save context information to the cache so you can recall it later without re-computing. Perfect for caching: codebase overviews, file summaries, project structure, frequently-accessed data, or "thinking" results like dependency analysis. The AI assistant can use this to avoid re-reading the entire codebase every time. Overwrites any existing value stored under the same key. Returns { key, stored_at, ttl } confirming the saved context. Example: remember_context("project overview", "This is a Next.js app with...") then later: recall_context("project overview"). Use recall_context to retrieve; use list_remembered to see all stored keys.

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 features, bugs, refactors, or any planned work. Call roadmap_list to see all open items, roadmap_next to get the next actionable item.

List all roadmap items, optionally filtered by status, priority, tag, or milestone. Returns items sorted by priority then creation date. Called automatically by session_start to show open work.

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 session start to immediately know what to work on next.

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 use to add notes/findings while working on an item.

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, similarity_score (0–1), and namespace. Returns an empty array if no entries meet the similarity threshold. Requires OPENAI_API_KEY (or compatible provider) and the Speed/Business tier with CACHLY_VECTOR_URL. Embeddings are computed server-side and never leave Germany (pgvector HNSW index). Example: "find all cached responses about password reset" or "what did we answer about pricing?". Use cache_get for exact key lookup; use smart_recall for brain lessons.

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 "Last session". Call this when ending a work session, before going idle, or before summarizing. Ambient Learning: if workspace_path is provided, reads git log since session start and auto-learns from commits.

Save a detailed handoff for the NEXT chat window / session. Stores: current progress, TODO list (done + remaining), changed files with descriptions, instructions for the next assistant, and any incomplete work. The next session_start automatically includes this handoff so the new window knows EXACTLY what happened and what remains. Call this BEFORE closing a chat window, especially if work is incomplete. This prevents the "continue" problem where new windows lose context, skip tasks, or produce broken code.

Single-call session briefing. Call this at the START of every session INSTEAD of multiple separate smart_recall/recall_best_solution calls. Returns: last session summary, recent lessons sorted by recency, relevant lessons for your focus area, brain health stats (counts of open failures and stale lessons), team telepathy (what teammates learned this week), predictive pre-warnings (if your focus area has known failure patterns), and memory crystals (compressed wisdom from old sessions). Also saves a session start marker so session_end can compute duration.

Semantically search cached context using natural language. instance_id may be omitted; the configured instance is used — never guess one.Instead of exact key matching, finds context by meaning. Example: smart_recall("how does authentication work") → returns cached auth architecture summary. Falls back to remember_context keys if no semantic match is found.

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_recall with "by <author>" so the team knows who learned it.

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, recency, and severity for each lesson. Use this to onboard new team members or find who knows about a topic.