TokenKnows
Distill AI coding sessions into weekly reports, ADRs and a knowledge graph - self-hosted
Connector by johnnywuj81 · GitHub account verified by the MCP Registry
Chalk Labs
Need help deploying TokenKnows?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/johnnywuj81-tokenknows
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.
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.
About
Reviews
Write a reviewNo 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
- 4 read · 1 write · 0 delete · 1 not yet classified
- Secrets
- 1 (API keys, tokens or passwords)
- Install scripts
- Not scanned yet
- Runs as
- Python package
Tools by what they do 6
Read from the source code; the running server may list different tools.
Read 4 · Look things up without changing anything.
get_assetget_asset_chapterslist_assetssearch_entity
Write 1 · Create, change, send or run things.
submit_session_events
Not yet classified 1 · We could not tell from the name and description.
distill_document
Secrets and settings it asks for
Secrets: values you paste in that let it act as you.
TOKENKNOWS_API_TOKEN
Other settings (environment variables or headers).
TOKENKNOWS_API_BASETOKENKNOWS_DEFAULT_PROJECTTOKENKNOWS_WEB_BASE
Tools (6)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
distill_document触发 backend 5-stage pipeline 蒸馏 events → 文档. Args: document_type: 7 类之一 (周报 / 技术方案 / ADR / 复盘 / 书籍 / Skill / 知识图谱) project_id: 项目 id; 不传用 default time_window: 时间窗 (this_week/last_week/last_7_days/last_14_days/last_30_days) model: 显式指定 model (e.g. "claude-sonnet-4-6"); 不传走 task 默认 Returns: { "asset_id": "...", "status": "generating", "title": "...", "view_url": "http://127.0.0.1:5173/projects/{pid}/documents/{aid}", "estimated_seconds": 60, "note": "可调 get_asset 轮询完成状态" }
get_asset读单个 asset 元数据 (不含 chapter content). 用于轮询 distill 完成状态. 完整内容用 get_asset_chapters 或读 resource.
get_asset_chapters读 asset 的所有 chapter (含 markdown content + layout). 对 knowledge_graph 类型, layout 含 nodes/edges/thumbnail_svg. 对其它 7 类, content 是 markdown 正文.
list_assets列项目下的蒸馏文档. Args: project_id: 项目 id; 不传用 default asset_type: 过滤 weekly_report/tech_design/.../knowledge_graph status: 过滤 generating/draft/in_review/approved/published limit: 1-100, 默认 20
search_entity跨文档实体搜索 (KG entity_registry). 例: search_entity('Alice') → 返回 Alice 出现在哪些 KG asset 里. Args: query: label / aliases 模糊匹配 project_id: 项目 id; 不传用 default entity_type: 过滤 person/event/concept/artifact min_assets: 仅返回出现在 ≥N 个 asset 的 (跨文档实体)
submit_session_eventsPersist conversation events into TokenKnows backend. See the `session_capture` skill in this plugin for full call-timing rules and examples (lazy-loaded, ~50 tokens at startup, full body only when LLM determines relevance). Args: events: 1-100 events. Each item: {content (required), title?, author_name?, event_type? (default "ai_conversation_turn"), source_type? ("claude_cowork" in Cowork, default "claude_code" elsewhere), source_ref?, external_id? (auto-hash), tags?}. project_id: optional override; defaults TOKENKNOWS_DEFAULT_PROJECT. Returns: {"ingested…
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Weekly downloads
- 29
- Last commit
- Jun 11, 2026 (5 months ago)
- Last release
- Jun 11, 2026 (5 months ago)
- Last package publish
- Jun 11, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Registry name
io.github.johnnywuj81/tokenknows- Version
- 0.3.0
- Auth
- API key
- Packages
- pypi tokenknows-mcp
- License
- MIT
- Repository
- github.com/johnnywuj81/tokenknows
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get TokenKnows running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
TokenKnows MCP server. Agent Mart. https://agentmart.dev/connectors/johnnywuj81-tokenknows (last updated 2026-10-24)