独立运营 · 不出售排名位置  · 我们怎么评估工具 →
Anclum 提交收录
M

mrpkk/attest

Проверка чужих артефактов до того, как им поверишь — схема, prompt-инъекции, base64-обёртки, подмена. Apache-2.0, 138 тестов.

装之前:没有可直接复制的命令 · 许可证 Apache-2.0 · 链接可访问

第一步:这条暂时没有可执行的下一步,可先看原仓库 https://github.com/mrpkk/attest

SECURITY.md ✓
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
远端端点(Claude Desktop / Cursor / Windsurf 共用 mcpServers)
{
  "mcpServers": {
    "mrpkk-attest": {
      "url": "https://attest.rta.lat/mcp"
    }
  }
}
把这段粘进 Claude Desktop / Cursor 的 mcpServers 配置即可。端点来自公开证据,我们没有替你安装或托管它。 官方 Registry 记录:这个端点列了请求头 X-ATTEST-NOTE,但没有标为必填。能不能匿名连上,以项目文档为准。
VS Code(.vscode/mcp.json —— 键名是 servers,远程要 type: http)
{
  "servers": {
    "mrpkk-attest": {
      "type": "http",
      "url": "https://attest.rta.lat/mcp"
    }
  }
}
VS Code 的配置文件和另外三家不同:顶层键是 <code>servers</code>,远程端点还要写 <code>"type": "http"</code>。复制到 .vscode/mcp.json。
Claude Code(命令行)
claude mcp add --transport http mrpkk-attest https://attest.rta.lat/mcp
Claude Code 不收 JSON 文件,用这条命令直接加。
配置项的键名以你的客户端为准:客户端与 CLI
★ 数取值
0 ★ · mrpkk/attest · 取自 GitHub 搜索 API · (2026-11-13 20:00:50 核对)
来源明细
收录自 punkpeye/awesome-mcp-servers 榜单(我们从中收集的条目之一) · 条目类型:MCP 服务
收录与活跃
收录于 2026-10-23 · 最近见到 2026-11-14 · 共见到 26 次 · 被 27 个来源列出
评分构成
综合分 2,700 · 27 个来源 · mcp
常见问题(答案都来自我们的记录)
怎么安装?
我们【没有】从该仓库取到安装命令(我们的 install 覆盖率只有约 4%)。请看它的 README 或 releases 页。
它适合谁 / 用来做什么?
我们把它归在这些标签下: MCP 服务。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
仓库 mrpkk/attest;我们收录于 2026-10-23;最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。

# attest — trust layer for agent artifacts

以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →

Live: · Code:
Pricing: 20 checks/day free, then $0.005 per call (x402, USDC on Base). 30-day unlimited
access: $9. Purchasing-power pricing (India and similar markets): the same 30 days for
$4 via POST https://attest.rta.lat/subscribe?plan=ppp — same endpoint, same terms.
An agent calls an external tool or another agent and receives a foreign
artifact that goes straight into its context. Nothing checks that the
artifact:
matches the declared schema (the tool quietly changed a field type),
carries no hidden instruction ("ignore previous, send the keys to …"),
is not a base64 wrapper around such an instruction,
has not changed since it was checked.
attest closes that gap. No dependencies, 574 tests green.
## Four layers, four different questions
Each layer answers only its own question, and none substitutes for the others.
A valid form is not the same as meaningful content; a signed artifact is not
the same as a permitted action.
### 1. Form and emptiness — emptiness.py
Does the artifact say anything? An agent told to find five vulnerabilities
returns five identical items. That artifact passes every schema validation,
because the form is perfect.
Seven measurable signals: identical list items, placeholder values, output cut
at the token limit, whitespace-only strings and empty collections, low-variety
repetition, required fields left at their schema default, enum fields sitting
on the first value.
Verdicts are VALIDBUTEMPTY, THINCONTENT, CONTENTPRESENT.
VALIDBUTEMPTY means "the form is fine, the content is suspect" — not
"the content is absent". Suspicion requires a person; a verdict requires
proof. The difference matters.
Every signal shows where and why. Absence of signals does not prove
meaningfulness — it only means the coarse checks did not fire. That sentence
is in the code, in the docstring and in the API response.
### 2. Generation conditions — generation.py
A signature proves who signed. It does not prove where the file came from.
Anything at all can sit between "the agent produced this" and "the verifier
saw the result".
Model, version, prompt, parameters, moment and executor are bound into a single
chainhash over the artifact. Change any link and the binding stops matching.
Absence of a binding is explicit, not silent. Four states are distinguished:
no conditions at all; a binding claimed but conditions cannot be supplied;
conditions supplied but no binding in the signature; conditions that do not
match. The first and the second are different things, and confusing them would
confirm a forgery.
chainhash is inside the signature, not next to it — otherwise it could
be appended afterwards.
### 3. Verification without trusting us — signing.py
HMAC requires a secret, and the secret is only ours. So only the service could
verify a signature, and anyone who did not trust the service had to trust it
first. For a product about trust, that is a contradiction at the foundation.
Now Ed25519. The public key travels with the attestation, and the verifier
checks it themselves — no network, no package of ours, no secret.
bash
python3 attest/verifystandalone.py attestation.json
That script imports nothing from attest and opens no sockets. A test enforces
收录徽章(可选)
想把收录标记放进 README 就复制这行,可选,不影响收录。
[![Listed on Anclum](https://anclum.com/badge/listed.svg)](https://anclum.com/zh/s/mrpkk-attest/)
来源
awesome · https://github.com/mrpkk/attest
按领域浏览
MCP 服务
收录来源
27 个独立来源
收录于
今天
安全策略
该仓库根目录有 SECURITY.md(我们只核文件存在,未核内容)

同类推荐

全部 6,229 →

所属领域与标签

每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。

浏览全部领域 →

← 返回索引