Proofable MCP

io.github.proofable由 GitHub 账号 proofable 发布v0.1.10更新于 Nov 7, 2026

Context and control for any AI. Agent identity, scoped access, and proof across tools.

已验证Streamable HTTP可网页运行安全与监控AI 与机器学习

概览

AI 生成的概览

Proofable 远程端点，让助手为已登录账户检查、创建和复用验证证明，并管理代理身份与权限。

可以做什么
  • 读取已登录资料、证明索引、代理与权限
  • 列出支持的验证检查及其所需输入
  • 检查钱包是否已有合格证明，或复用现有证明并给出下一步
  • 直接创建证明，或为需要其他签名者的检查做预备与提交
  • 搜索和读取证明，包括正文与评论
  • 更新证明元数据或可见性、投票与评论；检查、创建并挂载代理
适用场景
适合需要依据已有证明确认资格或访问权限、复用当前证明而不重复验证，或让助手在受限的代理身份与权限下执行操作的场景。
运行要求
在客户端添加远程 MCP 端点，无需本地安装包。多数工具需要先通过托管流程或安装命令登录，另有四个工具在未登录时可用。服务器与自动化场景可使用存于 PROOFABLE_ACCESS_KEY 的访问密钥，并以 Bearer 令牌发送。
安装前请注意
工具可创建证明、更改证明可见性（设为私有会撤销公开访问）、发表投票与评论、创建代理；除非明确要求上链，证明默认留在链下。访问密钥属于机密，不应粘贴到聊天或写入代码。读取私有上下文与证明正文需要登录。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Proofable MCP，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.proofable%2Fmcp/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "proofable": {
      "type": "http",
      "url": "https://mcp.proofable.me/mcp"
    }
  }
}

README

Proofable MCP

[npm] [License]

The trust harness for AI. Identity and governance for the agents you run, in every MCP client.

Connect Proofable once, and your agents can use your profile, proofs, permissions, and protected tools in Cursor, Claude, Codex, VS Code, ChatGPT, and any other MCP client.

Start

Open Set up Proofable, choose your client, and finish sign-in. Then ask:

text
Show my Proofable profile and the proofs I can reuse.

For a specific requirement:

text
Check whether I already have the proof needed for this task. Reuse it if it qualifies; otherwise show me the next step.

Connect

[Add to Cursor] [Install in VS Code]

Add https://mcp.proofable.me/mcp to any MCP client, or use a standard MCP configuration:

json
{  "mcpServers": {    "proofable": {      "type": "http",      "url": "https://mcp.proofable.me/mcp"    }  }}

The installer writes the same connection for supported clients:

bash
npx -y @proofable/sdk setup

Claude Code installs the server and the workflow skills together:

text
/plugin marketplace add proofable/mcp/plugin install proofable-mcp@proofable

Keep one Proofable connection per client. A marketplace plugin plus a manual entry creates a duplicate.

What agents can do

OutcomeTools
Load the signed-in profile and current contextproofable_context
Find supported checks and their required inputsproofable_verifiers_catalog
Check whether a qualifying proof already existsproofable_proofs_check
Reuse a current proof or get the next verification stepproofable_verify_or_guide
Create or refresh a proofproofable_verify
Prepare and submit a check needing another signerproofable_verify_prepare, proofable_verify_submit
Find and read proofsproofable_proofs_get
Update proof metadata or add feedbackproofable_proofs_update
Check, create, and load agent permissionsproofable_agent_link, proofable_agent_create, proofable_agent_mount

Call proofable_context once after connecting. Proofable reuses current proofs before starting another verification and returns Passed, Action needed, or Blocked.

The MCP tool reference lists every tool with its inputs and result shapes.

Servers and automation

Create an access key under Account → Access keys, store it as PROOFABLE_ACCESS_KEY, and send it as a Bearer token. Keep access keys out of source code, browser bundles, and chat.

json
{  "mcpServers": {    "proofable": {      "type": "http",      "url": "https://mcp.proofable.me/mcp",      "headers": {        "Authorization": "Bearer ${PROOFABLE_ACCESS_KEY}"      }    }  }}

Examples

  • Prompt injection test: hides AgentDojo attacks in a note your agent reads, runs the task under a scoped and a broad permission, and grades every run from its signed receipt.
  • Guarded agent action: makes one permission decision before host code runs a tool.

Build with Proofable

Use the Proofable SDK for application code, verification gates, and the CLI. This repository carries the MCP registry manifest, the host plugins, and the workflow skills; the server runs at https://mcp.proofable.me/mcp.

Support

Apache-2.0. Proofable is published by NEUS Network, Inc.

来源：README.md，提交 8460351

工具

12

proofable_context

Session context

Return the signed-in Proofable profile and its current read-only context: proof index, agents, permissions, and verifier summary. Use once after sign-in.

无需输入参数。

proofable_verifiers_catalog

Verifier catalog

Return supported check definitions with the inputs and networks each requires.

无需输入参数。

proofable_proofs_check

Check proofs

Does this wallet already have the required proofs? Returns pass or fail, not records. Reading proof bodies needs a signed-in session, which is what unlocks proofable_proofs_get; signed-out callers get this check and can sign in to go further. Omit the wallet when signed in.

输入参数gateIdhandlewalletminCountnamespaceverifiers必填requireAll

proofable_verify

Create proof

Create a proof directly for the signed-in account. Omit the wallet for your own account. If another signer is required, use proofable_verify_prepare and proofable_verify_submit.

输入参数datachainoptionsverifierIds必填walletAddresssignedTimestamp

proofable_verify_prepare

Prepare signature request

Prepare a signature request for the selected Proofable checks. Returns the exact signing string, timestamp, chain, and hosted fallback. This call does not submit the check or create a proof.

输入参数datachainoptionsverifierIds必填walletAddresssignedTimestamp

proofable_verify_submit

Submit signed verification

Submit a signed Proofable check using the same wallet, checks, data, and chain used to prepare it, plus the returned signing timestamp and signature. Creates a proof only when verification succeeds.

输入参数datachainoptionssignature必填verifierIds必填walletAddress必填signedTimestamp必填

proofable_verify_or_guide

Verify or get next step

Resolve a verification request for the selected Proofable checks. Returns current qualifying proofs when they exist; otherwise returns the single next step. This tool does not create a proof.

输入参数datachainoptionsrequireAllverifierIds必填walletAddress

proofable_proofs_get

Read proofs

Read a proof by qHash or search proofs by scope, tags, verifier, or text. With no filter, returns an index hint; scope=all pages metadata. Use include=content for proof bodies and includeComments with qHash for discussion. Omit identifier when signed in.

输入参数qtagsdepthlimitqHashscopeoffsetincludetraversetagPrefixidentifierverifierId另有 4 个

proofable_proofs_update

Update proof

Update a proof you own: title, tags, and visibility (public|unlisted|private). Setting visibility to private revokes public access, so confirm before making an already-shared proof private. Or leave feedback on an accessible proof. Send one kind of change per call: metadata, vote, or comment. Owners can vote on their own proofs. Delegated agents need manage_proofs.

输入参数voteqHash必填titleaddTagscommentparentIdremoveTagsvisibilitywalletAddressdisclosePortableProof

proofable_agent_create

Create agent

Create or import an agent on your profile. Default: signed-in account. Optional separate account and controls. Generate and retain any dedicated key outside Proofable, then pass only its public address. Keep the same agentId on retries.

输入参数chainpresetskillsagentId必填maxSpendservicesagentTypeexpiresAtreturnUrlagentLabelagentWalletdescription另有 11 个

proofable_agent_mount

Load agent context

Load the agent identity, permissions, skills, and context into this project.

输入参数agentIdagentWalletidentityQHashcontrollerWalletrequiredResources

版本历史

9
  1. v0.1.10最新Nov 7, 2026
  2. v0.1.8Nov 1, 2026
  3. v0.1.7Oct 11, 2026
  4. v0.1.6Oct 9, 2026
  5. v0.1.5Oct 8, 2026
  6. v0.1.4Oct 5, 2026
  7. v0.1.3Sep 29, 2026
  8. v0.1.2Sep 25, 2026
  9. v0.1.1Sep 16, 2026

评分

已满足适用检查项的 100%

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 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分