Skip to content

cachly — Explain it once. Every AI knows it. MCP server

io.github.cachly-dev/mcp-servercachly-devstreamable-httpv0.10.267Scanned

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

27 tools: 1 can delete or cancel things, 17 change things and 9 only read.

Tools: 1 delete, 0 irreversible, 17 write, 9 read.
  • Reads private data · 1
  • Reads text others write · 0
  • Can send data out · 0
  • 3 findings, 1 high

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the cachly — Explain it once. Every AI knows it. MCP server can do

The cachly — Explain it once. Every AI knows it. MCP server is published by the GitHub account cachly-dev. It has 27 tools. It can delete or cancel things (1 tool: forget_context) and create or change data (17 tools: cache_set, index_project, remember_context, learn_from_attempts and 13 more). 9 tools only read.

1 tool reads private data (smart_recall).

The fixed checks matched 3 findings, 1 of them high severity (install-script, sensitive-path and long-description). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 20, 2026, version 0.10.267.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

27 tools

Deletes or cancels 1Claude Code: deny
  • forget_contextDelete one or more cached context entries.No findings

    Why it is in this group

    • The description's first verb is "delete": a word for removing or ending something.
    Description, as the server wrote it
    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.
Changes things 17Claude Code: ask
  • autopilotGenerate a CLAUDE.md / copilot-instructions.md that makes any AI self-managing forever.No findings

    Why it is in this group

    • The description's first verb is "generate": a word for a change.
    Description, as the server wrote it
    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.
  • brain_doctorCheck the health of your AI Brain and get actionable recommendations.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
  • brain_from_gitBootstrap brain lessons from git history.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
  • cache_setSet a key-value pair in a running cache instance.No findings

    Why it is in this group

    • The name "cache_set" says "set": a word for a change.
    Description, as the server wrote it
    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).
  • cachly_toolRun any of cachly's specialist tools by name.1 finding

    Why it is in this group

    • The description's first verb is "run": a word for a change.

    Findings

    • Info

      The description is 2,142 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "..., brain_discover, brain_seed_starter, brain_graph, brain_set_pref, brain_get_pref"

      What this check looks for
    Description, as the server wrote it
    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
  • causal_traceRoot 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 exa…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
  • index_projectIndex 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.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
  • learn_from_attemptsStore a lesson AFTER any non-trivial task (deploy, debug, fix, decision); future sessions recall it.1 finding

    Why it is in this group

    • The description's first verb is "store": a word for a change.

    Findings

    • High

      The input schema at properties.file_paths.description refers to ".env".

      Matched text

      inputSchema.properties.file_paths.description: "...this lesson (e.g. ["infra/deploy.sh", ".env"])"

      What this check looks for
    Description, as the server wrote it
    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 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")
  • recall_best_solutionRecall the best known solution for a topic from past lessons.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote itContains invisible characters, shown as [U+…]
    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. ⚠[U+FE0F] 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.
  • remember_contextSave context information to the cache so you can recall it later without re-computing.No findings

    Why it is in this group

    • The description's first verb is "save": a word for a change.
    Description, as the server wrote it
    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.
  • roadmap_addAdd a new item to the persistent project roadmap stored in the Brain.No findings

    Why it is in this group

    • The name "roadmap_add" says "add": a word for a change.
    Description, as the server wrote it
    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.
  • roadmap_updateUpdate the status, priority, or details of a roadmap item.No findings

    Why it is in this group

    • The name "roadmap_update" says "update": a word for a change.
    Description, as the server wrote it
    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.
  • session_endSave a session summary when you finish working.No findings

    Why it is in this group

    • The description's first verb is "save": a word for a change.
    Description, as the server wrote it
    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.
  • session_handoffSave a detailed handoff for the NEXT chat window / session.No findings

    Why it is in this group

    • The description's first verb is "save": a word for a change.
    Description, as the server wrote it
    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.
  • session_startSingle-call session briefing for the START of a session: last summary, recent lessons, health.No findings

    Why it is in this group

    • The name "session_start" says "start": a word for a change.
    Description, as the server wrote it
    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: 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.
  • team_learnStore a lesson in a shared team brain so all team members benefit.No findings

    Why it is in this group

    • The description's first verb is "store": a word for a change.
    Description, as the server wrote it
    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.
  • team_recallRecall lessons from a shared team brain, showing who learned what.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote 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.
Only reads 9Show 9 read-only tools
  • brain_predictREAD-ONLY — no side effects, no writes, no external network calls.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    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.
  • cache_getGet a value from a running cache instance by key.No findings

    Why it is in this group

    • The name "cache_get" says "get": a word for reading.
    Description, as the server wrote it
    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.
  • list_rememberedList all cached context entries for this project.No findings

    Why it is in this group

    • The name "list_remembered" says "list": a word for reading.
    Description, as the server wrote it
    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_contextRetrieve previously saved context from the cache.No findings

    Why it is in this group

    • The description's first verb is "retrieve": a word for reading.
    Description, as the server wrote it
    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.
  • roadmap_listList all roadmap items, optionally filtered by status, priority, tag, or milestone.No findings

    Why it is in this group

    • The name "roadmap_list" says "list": a word for reading.
    Description, as the server wrote it
    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.
  • roadmap_nextGet the single most important next actionable roadmap item.No findings

    Why it is in this group

    • The description's first verb is "get": a word for reading.
    Description, as the server wrote it
    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.
  • smart_recallReturns the fixes, decisions and pitfalls this team already learned for the task at hand.Reads private dataNo findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.

    What it can reach

    • private-dataThe input names a file (input.context_files), and the tool reads: it reads files.
    Description, as the server wrote it
    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 or editing — with one line about the task, e.g. smart_recall("fix login redirect loop"). Finds lessons by meaning, not exact words. instance_id may be omitted (never guess one). Falls back to remember_context keys if no semantic match is found.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 19, 2026, 17:20 UTC, unchanged since Nov 19, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
18
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 18 tools that change things (1 destructive, 17 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.cachly.dev/mcp: tools/list returned 27 tools to an anonymous client, including forget_context (destructive), cache_set (write), index_project (write), remember_context (write), learn_from_attempts (write) and 13 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 high2 info
  • The input schema at properties.file_paths.description refers to ".env".

    Matched text

    inputSchema.properties.file_paths.description: "...this lesson (e.g. ["infra/deploy.sh", ".env"])"

    What this check looks for
  • InfoThe whole server

    The package.json has a "postinstall" script, which npm runs on install.

    Matched text

    scripts.postinstall: "node scripts/postinstall.js"

    What this check looks for
  • The description is 2,142 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "..., brain_discover, brain_seed_starter, brain_graph, brain_set_pref, brain_get_pref"

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools2 changed.~2 changedView diff

Install

Pinned to version 0.10.267. Values in angle brackets are yours to fill in.

claude mcp add --transport http cachly-dev https://mcp.cachly.dev/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http cachly-dev https://mcp.cachly.dev/mcp --header 'Authorization: <your-authorization>'

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__cachly-dev__cache_get",
      "mcp__cachly-dev__semantic_search",
      "mcp__cachly-dev__recall_context",
      "mcp__cachly-dev__list_remembered",
      "mcp__cachly-dev__smart_recall",
      "mcp__cachly-dev__roadmap_list",
      "mcp__cachly-dev__roadmap_next",
      "mcp__cachly-dev__brain_search",
      "mcp__cachly-dev__brain_predict"
    ],
    "ask": [
      "mcp__cachly-dev__cache_set",
      "mcp__cachly-dev__index_project",
      "mcp__cachly-dev__remember_context",
      "mcp__cachly-dev__learn_from_attempts",
      "mcp__cachly-dev__recall_best_solution",
      "mcp__cachly-dev__session_start",
      "mcp__cachly-dev__session_end",
      "mcp__cachly-dev__session_handoff",
      "mcp__cachly-dev__team_learn",
      "mcp__cachly-dev__team_recall",
      "mcp__cachly-dev__roadmap_add",
      "mcp__cachly-dev__roadmap_update",
      "mcp__cachly-dev__brain_doctor",
      "mcp__cachly-dev__causal_trace",
      "mcp__cachly-dev__autopilot",
      "mcp__cachly-dev__brain_from_git",
      "mcp__cachly-dev__cachly_tool"
    ],
    "deny": [
      "mcp__cachly-dev__forget_context"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as cachly-dev. Review it before you use it.

Capability tags behind 1 rule
  • mcp__cachly-dev__smart_recall private-data

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.cachly-dev/mcp-server/verify?hash=6740172e0adbeb154e4e7d046051c8c2ba3b7a9dd78cf579a59214fae9650f42" | jq -e '.changed == false'

Pinned hash 6740172e0adb, from Nov 20, 2026, 12:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.cachly-dev/mcp-server/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.cachly-dev/mcp-server
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.cachly-dev/mcp-server.svg)](https://radar.anlyon.com/servers/io.github.cachly-dev/mcp-server)

Source: MCP Registry · repository. Synced Nov 20, 2026, 12:17 UTC.

cachly — Explain it once. Every AI knows it. MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

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

No scan can promise that. What its definitions show: 27 tools, 18 of which can change, send or delete something, and 3 findings (1 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the cachly — Explain it once. Every AI knows it. MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: forget_context.

Can the cachly — Explain it once. Every AI knows it. MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the cachly — Explain it once. Every AI knows it. MCP server have?

27 tools: 1 destructive, 17 write, 9 read. forget_context, cache_set, index_project, remember_context, learn_from_attempts, recall_best_solution, session_start, session_end and 19 more.

Does the cachly — Explain it once. Every AI knows it. MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the cachly — Explain it once. Every AI knows it. MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the cachly — Explain it once. Every AI knows it. MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.