
Agent Core
io.github.kinbinghua-lgtm由 GitHub 帳號 kinbinghua-lgtm 發布v0.1.1更新於 Oct 24, 2026
Deterministic computation tools for AI agents. Zero dependencies, no network, read-only.
發布方自己的服務:core.blue
概覽
一個本機、零相依的 MCP 伺服器,為助理提供精確、確定性的運算工具:文字差異、雜湊、JSON 查詢、日期運算、正規表達式擷取等。
- 可以做什麼
- 對文字做差異比對與雜湊:精確的行級差異,sha256/sha512/sha1/md5 與 HMAC,輸出十六進位、base64 和位元組長度。
- 適用情境
- 當助理需要精確、可重現的答案,而語言模型靠猜測容易出錯時使用,例如計數、差異比對、雜湊、行事曆運算、CSV 解析、正規表達式擷取或單位與進位換算。
- 執行需求
- 透過 npx 以 stdio 在本機執行,需要 Node.js 18 或更新版本。無需 API 金鑰、環境變數、帳號或網路存取。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Agent Core,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
agent-core-mcp
Deterministic computation tools for AI agents. Exact diffing, hashing, JSON querying, calendar arithmetic, regex extraction under a hard execution deadline, CSV parsing, similarity scoring and unit/base conversion — as an MCP server.
Zero dependencies. No network. Read-only.
Why this exists
Language models are excellent at generating language and unreliable at exact, reproducible mechanical computation. That is not a capability gap — it is an architectural property. Asking a probabilistic system to count, diff, hash or do calendar math guarantees a certain rate of confident wrong answers.
This server moves those operations out of the model and into a deterministic engine.
The result is not a better guess. It is a different category of answer: one that is exact and reproducible.
There is a second reason, specific to the MCP ecosystem. The most-reported problems with published servers are credential exfiltration, undisclosed shell execution, dependency trees carrying known CVEs, and servers that hang the client. A server with no network, no credentials, no execution surface, and a bounding deadline on every operation cannot exhibit any of them.
Guarantees
The server publishes these as a machine-readable contract resource (agent-core://contract), so a client can verify what it is installing rather than trusting this file.
Install
No install step is required to run it. Requires Node.js 18 or newer.
Available from:
- npm —
agent-core-mcp - Official MCP registry —
io.github.kinbinghua-lgtm/agent-core-mcp - Source — github.com/kinbinghua-lgtm/agent-core-mcp
Configure
Claude Code
This repository ships a .mcp.json, so cloning it is enough:
Or add it to any project:
Claude Desktop, Cursor, VS Code, Windsurf, Continue, Zed
Same block, in that client's MCP configuration file. No API keys. No environment variables. Nothing to sign up for.
Tools
The ReDoS deadline
regex_extract accepts an optional budgetMs (default 1000, maximum 10000). Execution happens in a worker thread that is terminated when the deadline expires.
This is not a nicety. Node's regex engine cannot be interrupted, so a pattern with catastrophic backtracking blocks the main thread indefinitely. Measured growth for (a+)+$ against 'a'.repeat(n) + '!':
Roughly 4x per two additional characters. At n=40 it does not return. In an MCP server, which runs on the client's main thread, this freezes the user's editor. Process isolation plus termination is the only real boundary.
On expiry the response says so, and tells the caller how to fix the pattern:
Argument validation
Every call is validated against the tool's own JSON Schema before dispatch: required fields, primitive types, enum membership, numeric bounds and unknown properties. A malformed call returns a specific error instead of a confident wrong answer.
This matters because clients do not reliably honour schemas. A server that silently proceeds on a malformed call is worse than one that refuses it.
Examples
Exact diff
→ { "added": 1, "removed": 1, "lines": [ { "op": "equal", "aLine": 1, "bLine": 1 }, ... ] }
Big-integer conversion that stays exact
→ { "result": "20000000000001", "decimal": "9007199254740993" }
Business days between two dates
→ { "value": 5 }
Check a pattern before running it
→ { "risk": "high", "reasons": ["nested quantifier inside a repeated group — classic exponential backtracking"] }
Absent versus null
→ { "resolved": true, "found": false, "value": null, "type": "null" }
Design notes
Why stdio and not HTTP? A stdio server has no listening socket: no attack surface, no port to expose, no auth to get wrong, no data leaving the machine. For pure computation, HTTP would add risk and buy nothing.
Why no caching? Every call is stateless. Caching would introduce state, invalidation bugs and a place for data to persist. The operations are cheap enough that this is not a tradeoff.
Why refuse oversized input? An MCP server that hangs takes the client session with it. Refusing with an actionable message is strictly better than exhausting memory.
Why no dependencies at all? Every dependency is an ongoing obligation: updates, advisories, supply-chain risk, and one more reason the server might stop working. The Node standard library covers everything here.
Development
Both suites run on plain Node with no install step.
selftest.mjs checks hashing against published constants, big-integer round trips past 2^53, RFC 4180 quoting edge cases, Unicode word segmentation and calendar arithmetic. protocol-test.cjs drives the real handler through a fake transport and covers the handshake, version negotiation, every tool, argument validation, the ReDoS deadline, malformed frames, split frames, batches, concurrent request correlation and determinism.
Two bugs found by these suites, both retained as regression tests:
- A ReDoS in the word-segmentation regex. The original
textStatspattern was[\p{L}\p{N}][\p{L}\p{N}'’-]*— two adjacent, overlapping character classes. On a long letter run followed by a non-match it backtracked exponentially and hung the process. The analyzer shipped in this package did not catch it, because it statically inspects the pattern it is given and cannot see patterns written by hand in the source. The execution deadline above exists because of this. - Schema validation was absent. Missing required arguments were silently treated as absent values, so a caller that forgot
pathreceivedmissing-keyinstead of an error. Client-side schemas are not enforcement.
License
MIT — see LICENSE.
來源:README.md,提交 3c84e3c
工具
0版本歷史
1- v0.1.1最新Sep 16, 2026
評分
已滿足適用檢查項的 50%
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25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分
其他 Core 整合
core.blue
blue.core官方發布者
core.blue 的遠端 MCP 端點,提供每位客戶獨立的私有代理記憶「house」:可讀手冊、試用沙盒、查價格與建議,並申請 house。

Brevio Core
由 GitHub 帳號 Brevio-Ventures 發布
本機 MCP 伺服器,讓編碼代理掃描程式碼中反覆出現的代理式錯誤、解釋規則、列出規則,並把一次修正固化成守衛。

brain-core
由 GitHub 帳號 xy-claude 發布
本機 MCP 伺服器,為 Claude Code 代理提供跨工作階段的長期記憶,以 markdown 檔案加上本機 SQLite 與向量索引保存。

Scovant Core
由 GitHub 帳號 Scovant 發布
對網站進行被動式AI代理就緒掃描:robots、llms.txt、JSON-LD、MCP發現、安全性。AI 翻譯

ProofCore
由 GitHub 帳號 ProofCore-Protocol 發布
面向AI代理的TON區塊鏈零認證加密公證與證據層。AI 翻譯