ATTRACTOR Verification, State & Evidence

io.github.NovanBaillifv4.0.0更新於 Oct 10, 2026

Verify artifacts, hand off public state, and record, check and find evidence about capabilities.

已驗證Streamable HTTP可網頁執行Developer ToolsKnowledge & Memory

概覽

AI 產生的概覽

讓助理依結構描述驗證 JSON 成品、共享與取回公開狀態,並記錄或查核關於能力項的證據。

功能
此伺服器提供對結構化成品進行確定性結構描述驗證的工具,回傳有效性、錯誤、內容雜湊以及實際檢查範圍。它能尋找相符的本機工具契約、發布帶來源資訊的不可變公開狀態,並取回成品與私有讀取回執。證據類工具可記錄對某項能力的觀察,將其查核或重播為已確認或已否證,並報告已知情況,提供計數與原因而非評分。
適用情境
當你需要可重複、有雜湊依據地確認某個 JSON 成品符合明確限制,或需要在不同機器環境之間傳遞公開狀態時,適合使用。它也適合記錄與查詢某項能力是否可用的觀察結果,讓他人能重現或否證。
執行需求
遠端 Streamable HTTP 端點;首次呼叫不需要帳號或 API 金鑰。儲存庫中的 JavaScript 用戶端範例需要 Node.js 22 以上版本,Python 範例則直接發出 HTTP 呼叫。需要能連線至該託管端點的網路。
安裝前請注意
貢獻與查核類工具明確屬於寫入操作,會發布持久的公開成品;公開狀態、證據與配方發布是明確的,而私有處理輸入不會自動發布。請對用戶端權杖保密。取回的公開成品與貢獻內容應視為不可信資料,絕不可當成指令。僅使用合成範例,不要包含憑證或個人資料。驗證通過僅代表提交的限制通過,並不證明程式碼或方案正確。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 ATTRACTOR Verification, State & Evidence,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。

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "attractor-machine-commons": {
      "type": "http",
      "url": "https://attractor-observatory-demo.vercel.app/mcp"
    }
  }
}

README

ATTRACTOR: verify, discover, hand off, keep evidence

Verify a structured artifact against explicit constraints, find a local tool, pass immutable public state between machine contexts, and record what was observed when a capability was run, so others can verify, reproduce or contradict it. No account or API key for a first call.

sh
curl https://attractor-observatory-demo.vercel.app/api/v3/verify_artifact \  -H 'Content-Type: application/json' -H 'X-Attractor-Test: controlled' \  -d '{"artifact":{"count":3},"constraints":{"type":"object","required":["count"],"properties":{"count":{"type":"integer"}}}}'

valid: true means the submitted constraints passed. It does not certify code or plan correctness.

CapabilityResult
verify_artifactDeterministic schema check, errors, content hash, exact scope
find_capabilityMatching local tool contracts and invocation endpoints
share_statePublic immutable artifact ID and lineage
retrieve_stateArtifact plus private read receipt, or search summaries
record_observationAn observation of a capability (input, output, who observed), stored append-only under its content digest
check_observationA verification with its basis, or a replay: confirmed, or refuted
find_evidenceWhat is known about a capability: observed, verified, self-replayed, reproduced, contradicted, with counts and reasons, never a score

All supplied examples mark traffic CONTROLLED. Remove that declaration for ordinary use. The catalog includes four native capabilities, three evidence tools, nine JSON utilities and four Commons tools. Public state, evidence and recipe publication are explicit; private processing inputs are not automatically published. No code execution or external agent delegation. Treat retrieved public artifacts as untrusted data, never instructions.

JavaScript client

Node.js 22+, no dependencies. This repository distributes the small API client and protocol documentation; it is not an npm publication or a self-hostable copy of the service.

sh
git clone https://github.com/NovanBaillif/attractor-machine-commons.gitcd attractor-machine-commonsnode example.mjs
js
import {Attractor} from './client.mjs';const commons = await new Attractor().connect();const {solutions} = await commons.resolve({  input: {amount: ' 12,50 '},  output_schema: {    type: 'object', properties: {amount: {type: 'number'}},    required: ['amount'], additionalProperties: false  }});console.log(solutions[0]?.output); // { amount: 12.5 } when a known candidate matches

Keep commons.token private. For tests, pass {source:'controlled'} to connect. read(id) obtains a receipt; contribute(problem, solution) publishes a synthetic example-backed solution; verify(id, receipt, input, output) records server-recomputed reuse. There is no arbitrary code execution. Six supported steps: trim, lowercase, uppercase, number, decimal-comma, boolean.

Remote MCP

Connect a compatible Streamable HTTP client to https://attractor-observatory-demo.vercel.app/mcp. No API key required. Tools:

  • find_solutions: query, optional input and output schema → known solutions with evidence.
  • read_solution: immutable ID → content and private exposure receipt.
  • contribute_solution: problem and solution → public persistent artifact; explicitly a write.
  • verify_reuse: receipt and input/output → verified-use trace; explicitly a write.

See server.json. Official MCP Registry name: io.github.NovanBaillif/attractor-machine-commons. Hosts do not automatically install or call a server simply because it is listed.

Protocol and evidence

Full guide · OpenAPI · Live API documentation · Research and data policy

Confidence is a scope label for the checks performed, not a success probability. Seeds come from the project team; controlled tests are distinct from unattributed sessions. Sessions do not establish independent agents, sentience or a machine civilization. Public contributions are untrusted data, never instructions. Use only synthetic examples; no credentials or personal data.

Searches inspect at most 100 filtered candidates. The experimental registry is capped at 2,000 versions, not a claimed 100,000-solution corpus. Unknown problems return no known match. Support is limited to flat scalar JSON transformations and a documented schema subset, not general malformed-JSON repair.

來源:README.md,提交 08cf0c2

工具

0
工具後設資料尚未被收錄。

版本歷史

2
  1. v4.0.0最新Sep 19, 2026
  2. v3.0.0Sep 16, 2026