graphrag-ts citation provenance

io.github.sadofriod由 GitHub 帳號 sadofriod 發布v0.1.25更新於 Nov 3, 2026

針對 DOI 的分層來源撤稿與引用判定；證據不足時棄權。

AI 翻譯由 AI 模型根據下方的原文描述翻譯，可能有誤。

原文描述

Source-tiered retraction and citation judgments for DOIs; abstains when evidence is thin.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取知識與記憶

概覽

graphrag-ts citation provenance 的託管 MCP 服務（mcp.ashesborn.cloud）；可選 API 金鑰；Streamable HTTP；3 個工具。

暫無 AI 概覽：以下資訊來自註冊中心條目和服務本身。

端點
mcp.ashesborn.cloud
最近檢查

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 graphrag-ts citation provenance，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.sadofriod%2Fgraphrag-ts/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "graphrag-ts-citation-provenance": {
      "type": "http",
      "url": "https://mcp.ashesborn.cloud/mcp"
    }
  }
}

README

graphrag-ts

[Listed on mcpservers.org] [graphrag-ts MCP server]

Attribution is stored at write time, not asserted at read time.

graphrag-ts is a GraphRAG engine in TypeScript. It builds the knowledge graph in PostgreSQL, keeps source evidence on every node and edge, and answers with retrievable citations — or returns an explicit abstention when the coverage behind an answer is too thin to support it.

Benchmarks / 基准报告 English report · 中文报告

Hosted endpoint / 托管端点 https://mcp.ashesborn.cloud/mcp (anonymous tier: free integrity_paper_status, the two judgments answer with an x402 payment requirement; a keyed session unlocks them) · free DOI status: https://pay.ashesborn.cloud/api/v1/judge/paper?doi= · x402 wire format

[graphrag-ts-pg MCP connector – tool definition quality and endpoint health on Glama]

Try it in 60 seconds

No install, no API key, no model endpoint. Two ways in:

  • In a browser: Retraction Status — paste a DOI, get the source-by-source retraction status and the evidence tiers behind it, with no local model and no account.
  • From the command line:
bash
curl -s 'https://pay.ashesborn.cloud/api/v1/judge/paper?doi=10.1016/S0140-6736(97)11096-0'

The response is the paper plus every retraction record behind it, each with its source_tier and source_uri — the evidence the graph stores, not a model's recollection of it.

Point any Streamable HTTP MCP client at the hosted endpoint (public read tier, 20 requests/minute per IP):

json
{  "mcpServers": {    "graphrag-ts": { "url": "https://mcp.ashesborn.cloud/mcp" }  }}

A bearer API key unlocks the full tool set (graph queries, index jobs, memory writes). The two judgment tools also answer per call without a key via x402 payment ($0.02 / $0.10).

What it does differently

  • Postgres-native. Graph tables and pgvector live in the database you already operate — no Neo4j sidecar and no second store to keep in sync.
  • Incremental by construction. Rebuilds reuse unchanged community summaries, so the cost of a refresh tracks the delta rather than the corpus size.
  • Two retrieval shapes. Local: hybrid vector, keyword and graph retrieval over a community's evidence. Global: Map-Reduce over community summaries for corpus-wide questions.
  • Explicit abstention. Judgment verdicts carry source tiers and return an abstention when reference coverage is thin, instead of answering from a weak signal.
  • Evidence at chunk level. Entities and relationships keep the document and chunk they were extracted from, so an answer can be traced back to the text that produced it.

MCP tools

ToolAccessWhat it does
query_graphkeyedLocal hybrid retrieval against the latest published snapshot in a workspace
query_graph_globalkeyedCorpus-wide Map-Reduce retrieval over community summaries
submit_index_jobkeyedQueue Markdown from the configured input directory for indexing
remember_textkeyedQueue user-provided text explicitly; never reads chat history
get_index_jobkeyedStatus and safe error summary for an index job
integrity_paper_statuspublicRetraction status and identity for a paper
retraction_propagationpublic / x402Judge whether retraction evidence propagates to a paper
integrity_evidence_auditpublic / x402Audit the evidence path, source tiers and conflicts for a paper

Quick start — self-hosted

MCP with Docker Compose

The Compose stack starts PostgreSQL/pgvector and the MCP service. You must provide reachable chat and embedding endpoints; see the MCP guide for configuration, client setup, and workspace behavior.

bash
cp .env.example .env# Configure the database password and model endpoints in .env.docker compose up -d --buildcurl http://127.0.0.1:3000/healthz

Connect an MCP client to http://127.0.0.1:3000/mcp. For the optional local browser showcase, configure the models and run docker compose --profile showcase up -d --build --wait, then open http://127.0.0.1:8080. The showcase is a local demo, not an authentication layer; do not expose it to untrusted users.

Use the library

bash
pnpm installpnpm run db:generatecp .env.example .env# Configure DATABASE_URL and RAG_* model settings; see the guides below.pnpm run db:pushbun run examples/demo.ts

The library requires Bun, PostgreSQL with pgvector, and compatible chat and embedding endpoints. See the English guide or 中文指南 for environment setup, API examples, adapters, and tuning.

Overview

  • Markdown ingestion, entity/relationship extraction, and community detection
  • Full and incremental builds, with unchanged community summaries reused
  • Hybrid vector, keyword, and graph retrieval, plus corpus-wide Map-Reduce queries
  • MCP server with isolated workspaces and a local browser showcase

See the architecture guide for the pipeline and module details.

Benchmark

The reported in-corpus run reached 10/12 strict hits and 95.8% combined lexical recall on 12 questions from five indexed chapters. This is a small project benchmark, not human semantic grading or a cross-project comparison. The reports include methodology, per-query results, and limitations.

The English and Chinese reports are linked at the top of this page. To run the three-question Docker smoke benchmark, use pnpm benchmark:docker:quick with the model endpoints configured and loaded. See the MCP guide for prerequisites and the report for benchmark scope.

Listed on

Documentation

Contributing

Contributions are welcome through issues and pull requests. The project is organized around small, testable modules, so the most useful changes usually fit into one of these areas:

  • graph construction quality
  • retrieval quality and ranking
  • namespace isolation
  • model-loading robustness
  • documentation and examples

License

MIT

來源：README.md，提交 82fbaba

工具

3

integrity_paper_status

Look up one paper by DOI or OpenAlex id and return its identity (title, year, venue) plus every retraction record the graph holds for it, each with its source and source tier: A is an official registry, B an authoritative index, C an aggregator. Use it to check whether a paper is retracted and which sources assert it; use retraction_propagation to judge whether that retraction reaches a specific citing paper. Free in the public tier. Returns: paper identity and statuses[] with source, source_tier, is_retracted, retraction_date and source_uri; abstention_reason when the paper is not in the snapshot.

輸入參數doipaper_id

retraction_propagation

Judge whether a retraction propagates to a paper through its citation graph: retraction evidence is weighted by source tier, the citing context is checked for an acknowledgement, and the tool returns CONTESTED, SUPPORTED or ABSTAINED with the evidence path behind the verdict. Use it after integrity_paper_status when the question is "does this retraction reach this paper". It abstains instead of guessing when reference coverage is thin. Returns: verdict, confidence, the evidence path that produced it, and abstention details when the verdict is ABSTAINED. Paid: $0.02 per call (x402 on Base, POST /api/v1/judge); a keyed MCP session also unlocks it.

輸入參數doipaper_id

integrity_evidence_audit

Audit the evidence behind a paper's retraction picture: every source record with its tier and URI, the dates involved, conflicts between sources (an official registry and an aggregator disagreeing, or a citation acknowledging a retraction the graph does not propagate) and the coverage gaps that bound the conclusion. Use it when you must justify or challenge a verdict; for a one-line status use integrity_paper_status. Returns: evidence records with source tiers and URIs, detected conflict flags with codes and details, and the coverage that limits how strong the conclusion can be. Paid: $0.10 per call (x402 on Base, POST /api/v1/judge); a keyed MCP session also unlocks it.

輸入參數doipaper_id

版本歷史

2
  1. v0.1.25最新Nov 3, 2026
  2. v0.1.22Oct 29, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分