Skip to content
Agentmart
Submit a tool

Knowl

Persistent memory for AI agents, for code, research and everyday life.

Connector by dat999zx · GitHub account verified by the MCP Registry

IndexedApache-2.0Local (stdio)Remote (HTTP)★ 100
Write a review

Install

Works with Claude Code, VS Code, Codex, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/dat999zx-knowl

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://api.knowl.cloud/mcp/ Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Persistent memory for AI agents, for code, research and everyday life. Stale facts retire.

Use cases: agent-memory, knowledge-base

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
17 read · 7 write · 3 delete · 10 not yet classified
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Tools by what they do 37

Read from the source code; the running server may list different tools.

Read 17 · Look things up without changing anything.

  • knowl_cloud
  • knowl_conflicts
  • knowl_context
  • knowl_evidence_list
  • knowl_fleet
  • knowl_gc_preview
  • knowl_query
  • knowl_recent
  • knowl_resume
  • knowl_session_list
  • knowl_skill_list
  • knowl_skill_read
Show 5 more tools
  • knowl_state
  • knowl_timeline
  • knowl_transcript_read
  • knowl_transcript_search
  • knowl_workspace

Write 7 · Create, change, send or run things.

  • knowl_decide
  • knowl_feedback
  • knowl_ingest_atoms
  • knowl_skill_create
  • knowl_store
  • knowl_synthesize
  • knowl_task_start

Delete 3 · Delete, drop, revoke or wipe things.

  • knowl_gc_apply
  • knowl_skill_run
  • knowl_update

Not yet classified 10 · We could not tell from the name and description.

  • knowl_dissent
  • knowl_drift
  • knowl_handoff
  • knowl_hook
  • knowl_impact
  • knowl_ingest
  • knowl_park
  • knowl_session_finish
  • knowl_task_checkpoint
  • knowl_task_finish

Network hosts it talks to 1

  • api.knowl.cloud · found in remote endpoint, install command

Files it touches

  • Any path the agent passes to its tools

Tools (37)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • knowl_cloudCloud workspace publishing

    Check this repo's cloud workspace connection, or change what is queued for the team. `status` is local-only and instant -- use it before telling a user anything about what is or is not shared, because knowledge is staged automatically as it is written and sync runs on its own, so the answer changes without you. `stage` records the intent to publish and sends nothing; it is a dry run unless you pass apply. `unstage` takes an atom back out of the queue and is always safe: it sends nothing and unpublishes nothing. It cannot send, retract, pull, connect or sign in: those are the user's to run (`kn…

  • knowl_conflictsread-only

    List contradictions: declared exclusive conflict keys; polarity pairs (the same title asserted both ways, kept side by side); verified facts retired in the last 14 days, each with what replaced it and whether that replacement is still active; and same-subject active pairs with a verified side, which the write path keeps side by side instead of letting either retire the other. Use when a write reports an overlapping item left active, or when memory gives contradictory answers. A wrong retirement is undone by storing the correct fact with supersedes naming its replacement; a side-by-side pair is…

  • knowl_contextToken-budgeted context packread-only

    Fill an explicit token budget with diversified project context. Use only when you have a budget to fill -- briefing a subagent, or packing a fixed-size prompt. For a specific question use knowl_query instead: this spreads across categories to fill the budget rather than ranking for one subject, so it is deliberately broader and less precise.

  • knowl_decide

    Record a confirmed project decision -- what was chosen, why, and what was rejected. Use this rather than knowl_store when the reasoning and the alternatives are the point; reasoning is required here and optional there. Record only settled decisions, not options still under discussion. Needs no Knowl AI configuration. When this decision reverses or replaces an earlier one, pass that item id as `supersedes` so the superseded decision is retired in the same write; never leave two active decisions contradicting each other. The result reports any decision left active beside this one and the exact c…

  • knowl_dissentContest a linked repo's item

    Contest a linked repo's knowledge item without editing it. Use when a query returns another repo's item you believe is wrong: editing it is refused, and a dissent is the way the finding reaches its owner instead of being lost. Recording one writes only in THIS repo and changes nothing in theirs, but from then on every query returning that item -- in any repo here -- carries the dispute, so the next reader sees the objection before relying on it. The owner ends it by superseding the item (which is why there is no accept action) or by rejecting the dissent. Workspace-local: an item owned by a cl…

  • knowl_driftCheck memory against code changes

    Which stored knowledge this branch may have invalidated: atoms whose cited files the diff since `since` deleted or moved away, plus symbol evidence that no longer resolves. Use before opening a pull request, before knowl_task_finish on work that touched code, and when the user asks what a change breaks. An atom whose file was merely edited is deliberately NOT reported — that was two thirds of all matches and made the signal unreadable — so an empty result means nothing it cites went away, not that nothing changed. Previews by default; `apply` marks the matches as needing review so the next ses…

  • knowl_evidence_listread-only

    List the evidence linked to one knowledge item. Use before relying on an item that is low-confidence, contested, or old enough that its support matters more than its claim.

  • knowl_feedback

    Record append-only usefulness feedback only after a retrieved item was actually used, rejected, or caused a correction.

  • knowl_fleetOther agent sessions running nowread-only

    The other live agent sessions on this machine (Claude Code, Codex, Cursor and any other host with Knowl hooks): what each is working on, the files it is editing this turn, the problem it has claimed, and whether it can be messaged. Use before fixing an error that may be shared, before changing hooks, config, migrations or the knowl install, or when the user asks who else is running. A session marked messageable is reachable with SendMessage(to:name); SendMessage(to:name, notify_when_idle:true) waits for it to finish. Raise the rest with the user instead.

  • knowl_gc_applyDelete retired memorycan change or delete data

    Apply knowledge garbage collection only after knowl_gc_preview and explicit user approval; this may purge, archive, or compress records. Purge is the one action with no undo, so it deletes nothing unless `purgeItemIds` names the ids the preview listed and the user approved. Archive and compress still run without it.

  • knowl_gc_previewPreview retired-memory collectionread-only

    Preview knowledge garbage collection recommendations without changing the database. Use to find duplicate, stale, or cold memory before applying GC. Returns `purgeItemIds`: the ids knowl_gc_apply will not delete unless they are handed back to it.

  • knowl_handoffHand off to the next session here

    Park the current workstream so the next session in this project picks it up. Delivered once, then archived - this is a pass, not a durable note. Store anything worth keeping with knowl_store.

  • knowl_hookSession lifecycle hook

    Internal: the target of the host's lifecycle hooks when hooks.transport is mcp. The host calls it on every tool event; an agent never should -- calling it records a session event that did not happen.

  • knowl_impactChange-impact findings

    Change-impact findings: code a live session read that has since moved underneath it. Pass resolve to adjudicate one. A certain-tier finding also refuses the next edit to that file until you re-read it, so listing them here is how you see what is about to be blocked and why.

  • knowl_ingest

    Process explicitly supplied raw source text through the configured Knowl AI pipeline. Use only for an explicit ingestion request; never silently ingest the current conversation or prompt.

Show 22 more tools
  • knowl_ingest_atoms

    Store pre-extracted structured knowledge atoms from an MCP client. Do not store raw chat transcripts; extract durable facts, decisions, constraints, architecture, state, skills, and batch store implementation summaries during execution or after each completed subtask. This is the preferred MCP ingestion path and does not require Knowl AI configuration. When an atom corrects or replaces knowledge a query already returned, set `supersedes` on that atom to the outdated item id so it is retired in the same write; never leave two active items asserting different values for the same thing. The resul…

  • knowl_parkPark work under a key

    Park a workstream the user means to return to. Mints a short key and returns a line to hand them verbatim. Unlike knowl_handoff, this is not consumed by resuming and works from any directory, any number of sessions later.

  • knowl_queryread-only

    Description is built at runtime.

  • knowl_recentread-only

    Get compact recent session context only when lifecycle bootstrap is unavailable (including manual mode) or an explicit refresh is needed.

  • knowl_resumeResume parked work by keyread-only

    Resume a parked workstream from its key. Call this as soon as a user supplies something that looks like a resume key. With no key, lists what is parked in this project.

  • knowl_session_finish

    Finish and optionally promote a manual memory session you explicitly own. Never call this for a hook-owned session: when verified lifecycle hooks are active they finalize it themselves, and finishing it here closes a session out from under them.

  • knowl_session_listread-only

    Browse this project's past Claude Code sessions as an inventory: best-known name (a user rename beats a generated title), the opening ask, status, any declared session card, last activity, and what each session promoted into memory. Use to answer 'which session was about X' or to choose between resuming and starting fresh - then knowl_transcript_search with that sessionId to read into it. Filters over intent only; for content questions use knowl_transcript_search.

  • knowl_skill_create

    Create and index a learned file-backed skill only when the user explicitly requested a reusable workflow to be codified.

  • knowl_skill_listread-only

    List learned file-backed skills from `.knowl/skills`, name and purpose only. This is a stable MCP bridge so old sessions can discover newly created skills; read one with knowl_skill_read for its manifest and instructions.

  • knowl_skill_readread-only

    Read one learned skill package from `.knowl/skills/<name>/`, including `skill.json` and `SKILL.md`. Read a skill before running it, so knowl_skill_run executes an entrypoint you have seen rather than one you guessed at.

  • knowl_skill_runcan change or delete data

    Run an approved learned-skill entrypoint. A skill must be approved by the user with `knowl skill approve <name>` before it will run, and any edit to the package revokes that approval. Only an entrypoint whose author set `autoRun: true` will run; that is not the default. If the call is refused, relay the approval command to the user rather than trying to work around it.

  • knowl_stateWhole-project memory overviewread-only

    Get the full current active state of the project. Use for broad project-memory summaries, status checks, or full-state requests; prefer knowl_query for specific factual questions.

  • knowl_store

    Store one concise structured knowledge atom directly, not raw chat transcripts. Use immediately after discovering durable project knowledge or completing each subtask, not only at the end. This is deterministic and does not require Knowl AI configuration. When this atom corrects or replaces knowledge a query already returned, pass that item id as `supersedes` in this same call so the outdated item is retired in one write; never leave two active items asserting different values for the same thing. The result reports any item left active beside this one and the exact call to retire it.

  • knowl_synthesize

    Create or refresh one deterministic evidence-backed project understanding. Use only for a scope the user explicitly asked to have synthesised -- never as background tidy-up, and never to summarise a session. This never runs automatically on normal writes.

  • knowl_task_checkpoint

    Checkpoint meaningful progress or a blocker in a manual work loop using the taskId from knowl_task_start. Never use for a hook-owned session or routine command noise.

  • knowl_task_finish

    Finish one manual work loop exactly once after verification using the taskId from knowl_task_start. Never use for a hook-owned session.

  • knowl_task_start

    Start one manual work loop for multi-command or resumable work when verified lifecycle hooks are unavailable. Returns relevant memory and a taskId. Never use for a hook-owned session.

  • knowl_timelineread-only

    Read one item's immutable assertion history: what it claimed, when, and what superseded it. Use when memory looks contradictory or you need to know whether a fact changed -- knowl_query answers what it says now, this answers how it got there.

  • knowl_transcript_readread-only

    Read one transcript message and the turns around it. Pass a locator from knowl_transcript_search exactly as it was returned.

  • knowl_transcript_searchread-only

    Search this repo's past Claude Code session transcripts. Use after knowl_query misses. Returns pointers into the session files; store anything worth keeping with knowl_store.

  • knowl_updatecan change or delete data

    Update the metadata, status, or content of an existing knowledge item. Use immediately when execution reveals stale or contradicted memory instead of adding duplicates. To retire an outdated item in favour of one you just stored, call this with `id` set to the NEW item and `supersedeId` set to the OUTDATED item.

  • knowl_workspaceread-only

    Describe the local multi-repo workspace this repository belongs to: which repos are linked, which are present on this machine, and what they have been asking each other for. Use it when a query returned rows keyed by another repo and you need to know what that repo IS, or before deciding where knowledge belongs. Read-only: it links nothing, unlinks nothing and shares nothing. Linking repos and promoting knowledge to them are the user's to run (`knowl workspace add`, `knowl workspace promote`).

Signals

Stars
100
Forks
7
Open issues
2
Weekly downloads
713
Last commit
Oct 21, 2026 (7 days ago)
Last release
Oct 21, 2026 (7 days ago)
Last package publish
Oct 21, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.dat999zx/knowl
Version
5.28.1
Auth
Auth not stated
Packages
npm @dat999zx/knowl
License
Apache-2.0
Repository
github.com/dat999zx/knowl
Website
knowl.cloud
First seen
Oct 24, 2026
Last checked
Oct 25, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Knowl MCP server. Agent Mart. https://agentmart.dev/connectors/dat999zx-knowl (last updated 2026-10-25)