
Agent Core
io.github.kinbinghua-lgtm由 GitHub 账号 kinbinghua-lgtm 发布v0.1.1更新于 Oct 24, 2026
Deterministic computation tools for AI agents. Zero dependencies, no network, read-only.
发布方自己的服务:core.blue
概览
一个本地、零依赖的 MCP 服务器,为助手提供精确、确定性的计算工具:文本差异、哈希、JSON 查询、日期运算、正则提取等。
- 可以做什么
- 对文本做差异比较与哈希:精确行级差异,sha256/sha512/sha1/md5 与 HMAC,输出十六进制、base64 和字节长度。
- 适用场景
- 当助手需要精确、可复现的答案,而语言模型靠猜测容易出错时使用,例如计数、差异比较、哈希、日历运算、CSV 解析、正则提取或单位与进制换算。
- 运行要求
- 通过 npx 以 stdio 在本地运行,需要 Node.js 18 或更高版本。无需 API 密钥、环境变量、账号或网络访问。
安装
在 SourceWeft 中
- 打开 控制台中的 Agent Core,将其添加到工作区。
- 为需要使用其工具的对话启用该服务。
Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。
其他 MCP 客户端
参照 仓库 中的启动说明。
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.
来源:README.md,提交 3c84e3c
工具
0版本历史
1- v0.1.1最新Sep 16, 2026
评分
已满足适用检查项的 50%
该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。
- 近 30 天内可连通25 分
请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。
- 已声明认证方式10 分
请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。
- 已列出工具15 分
请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。
- 描述必需15 分
- 图标10 分
- 文档15 分
- 许可证10 分
其他 Core 集成
core.blue
blue.core官方发布者
core.blue 的远程 MCP 端点,提供每位客户独立的私有智能体记忆“house”:可读手册、试用沙盒、查价格与建议,并申请 house。

Brevio Core
由 GitHub 账号 Brevio-Ventures 发布
本地 MCP 服务器,让编码代理扫描代码中反复出现的代理式错误、解释规则、列出规则,并把一次修复固化为守卫。

brain-core
由 GitHub 账号 xy-claude 发布
本地 MCP 服务器,为 Claude Code 智能体提供跨会话的长期记忆,以 markdown 文件加本地 SQLite 与向量索引保存。

Scovant Core
由 GitHub 账号 Scovant 发布
对网站进行被动式AI代理就绪扫描:robots、llms.txt、JSON-LD、MCP发现、安全性。AI 翻译

ProofCore
由 GitHub 账号 ProofCore-Protocol 发布
面向AI代理的TON区块链零认证加密公证与证据层。AI 翻译