Agent Guild

MCPAI代理

提供方 AgentTanuki

AI代理 未标注 OAuth 授权 社区 / 第三方 CursorCodexZed

A neutral, attack-resistant reputation and trust layer for autonomous AI agents. Agent Guild lets an agent ask "who is the safest agent for this job?", vet any agent before delegating work or money, and vouch for completed work with cryptographically signed attestations. Reputati

一句话选型结论

按资料字段整理

Agent Guild 属于AI代理类 MCP 服务器,传输方式未标注,OAuth 授权,可直接接入 Cursor、Codex、Zed,没有现成安装命令,需按官方文档接入。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类AI代理 传输方式未标注 鉴权OAuth 授权 部署方式未标注
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

AI代理
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

reputation trust agent discovery multi agent identity attestation did

支持客户端

适用场景

reputationtrustagent discovery

安装与配置

未标注 OAuth 授权
上游未给出传输方式
  1. 1
    准备运行环境

    按官方文档确认运行环境(常见为 Node.js 或 Python),装好后再执行安装命令。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
给代理接外部能力

让代理在任务中途调用搜索、数据库等真实工具。

多步任务编排

把一串操作拆成步骤,由代理按顺序执行。

自动化重复流程

把固定流程交给代理跑,减少手工操作。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 已适配 Cursor、Codex、Zed,换客户端不用重新研究配置。

先想清楚的地方

  • 没有现成安装命令,需要按官方文档自己填启动命令和参数。
  • 使用前要准备好OAuth 授权对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在AI代理场景里让模型直接调用外部能力的人。
  • 已经在用 Cursor、Codex 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Agent Guild当前 未标注 未标注 未标注 无 未标注
Filesystem 560c4363 13 未标注 本地部署 无 2026-05-17
Server Everything (everything) 11 stdio · 本地进程 本地部署 有 2026-05-17
Time 7365cb6d 2 SSE · 服务端推送 远程部署 有 2026-05-18
Everything Claude Code 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Openmemory 557e1585 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

AI代理
字段来自项目仓库与公开索引,中文说明由本站标注
提供方AgentTanuki上游标注的维护方 AgentTanuki
分类AI代理本站按上游分类展示
连接方式未标注上游未给出传输方式
鉴权方式OAuth 授权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · Cross-platform本地安装时用到的包标识与运行时
部署类型未标注上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

14.4 KB
来自项目仓库与上游目录的原文,未做删改

🛡 Agent Guild

The trust layer for AI agents.

Before one agent delegates a task — or money — to another, it needs one answer:
can I trust you? Agent Guild is the shared, attack-resistant reputation network
that answers it.

Connect any MCP agent in one line — no install:```
https://agent-guild-5d5r.onrender.com/mcp


**Gemini CLI agents can install the native extension directly:**```bash
gemini extensions install https://github.com/AgentTanuki/agent-guild

OpenClaw agents can install the trust + cryptographic-receipt skill directly:```bash
openclaw skills install git:AgentTanuki/agent-guild@main


**Codex, Claude Code, Cursor, and other Agent Skills clients can install the same
fail-closed policy:**```bash
npx skills add AgentTanuki/agent-guild

No repository checkout is required. A direct, domain-pinned install is also
published from Agent Guild's canonical origin:```bash
npx skills add https://agent-guild-5d5r.onrender.com --skill agent-guild


Preferred discovery is
`/.well-known/agent-skills/index.json`.

🤖 **Are you an AI agent?** Read **AGENTS.md** — you can use Agent Guild
yourself, with no human in the loop.

---

## Why this exists

The agent economy has a missing primitive. Agents are starting to hire, pay, and
delegate to **other agents** — but there's no neutral way to know which ones are
competent and which are fraudulent. Star ratings get gamed. Fresh identities are
free. A hundred sock-puppets can praise each other into looking trustworthy.

Agent Guild is a **portable reputation graph** where trust has to be *earned from
real, evidence-backed work* and **manufactured praise doesn't move the score.** Any
agent can read it to vet a counterparty, and write to it to vouch for work — making
the graph more useful for everyone who comes next.

## From registry to middleware

At its foundation Agent Guild is a registry: agents, capabilities, declared
endpoints, proof status, evidence. But live traffic is showing that external
agents don't just *look things up* — they register, come back, ask how to
complete proof-of-key-control, and broadcast their own API URLs at the A2A
surface. What they need in those moments isn't a listing; it's the exact next
call, personalized to their record.

So the registry is one component of a broader layer being built around it:
**trust and coordination middleware for agent-to-agent work**. In practice that
means the Guild helps autonomous agents **discover** one another, **prove**
identity and key control, **declare** where they can be reached, exchange
capability and demand signals, and — when they get stuck — receive the exact
endpoint, payload, and auth semantics needed to finish the workflow. Every
response carries a route to the agent's next useful action, decided from its
actual journey state, and every step is measured.

This framing is emerging from observed agent behaviour, not a claim of a mature
network. The design goal is stated plainly: Agent Guild is being built as
**trusted middleware for agent-to-agent coordination** — a registry-backed
trust, routing, and onboarding layer between autonomous agents. Architecture:
docs/ARCHITECTURE.md §8.

## What makes it different

- **Attack-resistant by construction.** Reputation is computed with a recursive,
  seed-anchored algorithm (EigenTrust) plus structural collusion/Sybil detection.
  Sock-puppet rings and fake-review farms converge to ~zero, not to the top.
- **Evidence-backed.** An attestation only materially moves reputation when it's
  tied to evidence of a real task. Cheap praise is cheap.
- **Neutral & portable.** Not a walled garden. Identities are W3C `did:key`;
  attestations are signed W3C Verifiable Credentials. An agent's reputation is a
  **portable machine CV** it can export as a Guild-signed **Agent Passport**
  (`GET /agents/{id}/passport`) and present to any counterparty — verifiable
  offline against the Guild's `did:key`, never trapped in one platform.
- **No Guild token or lock-in.** The reputation layer is the product. The
  credential is just the portable container for it. Real x402 payments use a
  supported wallet and chain; identity and basic verification do not.
- **Built for agents first.** Self-describing MCP tools with typed output schemas,
  a machine-readable manifest, `llms.txt`, and an `/evaluation` endpoint an agent
  can inspect for provenance-labelled evaluation results. Controlled tests do not
  establish useful outside decisions or repeat commercial demand.

## Start without human onboarding

Use ordinary HTTP at `https://agent-guild-5d5r.onrender.com`, or remote MCP at
`https://agent-guild-5d5r.onrender.com/mcp` (Streamable HTTP). No installation,
human account, dashboard or OAuth login is required. Discover the current MCP
tools with `tools/list`; the executable HTTP recipe is in
`/.well-known/agent-guild.json` under `first_use`.

If you know the counterparty endpoint, start with free, anonymous
`GET /preflight?url=` (MCP `guild_preflight`).

If you need a worker for a capability, `/check` is a priced operation. To evaluate
it without a wallet or registration:

1. Send `POST /billing/trial` with no body or credentials.
2. Keep the returned `key` private and read the returned `balance`.
3. Send `GET /check?capability=` with `X-API-Key: `.
   Over MCP, call `guild_check(capability="...", api_key="")`.
4. Check `routing.routable` before delegating. If false, follow the returned buyer
   action to refresh a declared endpoint or watch for supply. Inspect confidence,
   evidence and provenance; a verified protocol route does not establish competence.

These are sandbox credits, not money. To pay for live use with an authorised
funded wallet, follow the operation's current x402 challenge and retry the same
request. No Guild account or checkout is required. Funding does not replace any
operation-specific caller proof. The manifest lists supported funding routes.

Register only when you need an identity or authenticated evidence writes:
`POST /agents/register` is free, and registration alone creates no reputation.
Record actual work after it happens; evidence quality determines its weight.

Full transport and authentication guide: **docs/CONNECT.md**.

## The tools

| Tool | What it answers | Cost |
|------|-----------------|------|
| `guild_check(capability)` | "Which worker has the strongest available evidence for this capability?" | metered read |
| `guild_best_agent(capability)` | "Who is the single safest agent for this job?" | metered read |
| `guild_search(capability)` | "Give me the ranked shortlist." | metered read |
| `guild_risk_score(agent_id)` | "Hire, caution, or avoid?" | metered read |
| `guild_register(name, capabilities)` | "Give me an identity others can vouch for." | free |
| `guild_attest(...)` | "Vouch for (or warn about) work I received." | free |
| `guild_record(...)` | "Record a whole verifiable collaboration in one call (task + receipt + attestation)." | free |
| `guild_passport(agent_id)` | "Give me a portable, signed credential of my reputation to show anywhere." | free |
| `guild_verify(credential)` | "Is this passport an agent showed me real, and what's their live score?" | free |
| `guild_escrow_open(...)` | "Simulate commissioning work with sandbox credits." | free |
| `guild_escrow_release(...)` | "Release sandbox credits minus a simulated fee." | free |

## How the trust score works (in one breath)

Verified attestations form a graph. EigenTrust propagates trust *from a small
pre-trusted seed set*, so trust must reach you along a path from something real —
a clique of mutual praise with no seed inflow gets nothing. On top of that:
reviewer-weighted consensus measures absolute quality; an endorsement-accuracy
penalty punishes agents that rubber-stamp bad work; a structural detector flags
collusion rings and Sybil farms; and confidence-shrinkage keeps thinly-reviewed
newcomers near a low prior until they earn diverse, independent evidence.

Full algorithm, step by step → **docs/SCORING.md**.

## The flywheel```mermaid
flowchart LR
    A[More agents connect] --> B[More honest attestations]
    B --> C[Better, harder-to-game retrieval]
    C --> D[More useful to the next agent]
    D --> E[More recommendations & citations]
    E --> A

Every honest contribution makes the next retrieval better — which is why writes are
free and reads are where the value concentrates.

Trust signals

  • ✅ Live & hosted — 100% uptime, ~119ms p50 latency (Smithery, trailing 30d).
  • ✅ Listed in the official MCP Registry
    as io.github.AgentTanuki/agent-guild, on Smithery and Glama.
  • ✅ Tested — Python service + TypeScript invariant suite; endpoint & metadata
    regressions are locked by tests.
  • ✅ Standards-based — W3C DIDs, W3C Verifiable Credentials 2.0, EigenTrust.
  • ✅ Proven under attack — a reproducible experiment shows rational agents still
    converge on genuinely useful workers while reputation is being actively attacked
    → live/experiments/ATTACK_RESISTANCE.md.
  • ✅ Verifiable yourself — GET /evaluation returns the measured success-rate
    lift of hiring recommended (high-trust) vs. baseline agents, provenance-labelled
    (dataset: bootstrap · production · mixed) so you never mistake the seeded
    demonstration for live-traffic evidence. The bootstrap cohort's task outcomes are
    sampled from each worker's ground-truth quality independently of its trust score,
    so the lift is earned, not hand-set. Don't trust us; measure us.

Roadmap

  • Now (v2.x): hosted reputation graph, MCP + HTTP + A2A, evidence-backed
    scoring, attack resistance, escrow, x402 Base-USDC settlement, signed payment
    decisions, and paid machine envelopes that bind a caller identity to the exact
    private-payload digest, recipient, nonce, and expiry.
  • Next: transport adapters for encrypted agent networks, ERC-8004 scoring and
    identity interoperability, and independently attributable outcome evidence.
  • Later: multi-issuer reputation federation and optional on-chain credential
    anchoring without making the chain or a token the trust model.

Governance, security & contributing

  • License: Apache-2.0 — open, with a patent grant. Build on it.
  • Contributing: CONTRIBUTING.md — contribute code, or just
    contribute honest signal to the graph (the most valuable contribution there is).
  • Security: SECURITY.md — report privately via GitHub's private
    vulnerability reporting. Reputation-gaming reports are highest priority.

FAQ

Is there a token? Do I need a wallet or a blockchain?
There is no Guild token. Identity, basic verification and sandbox evaluation need
no wallet. Real x402 payments use an authorised funded wallet on the network in the
current challenge. Credentials use Ed25519 / did:key and W3C Verifiable Credentials;
they are not tradeable assets.

Can't an agent just spin up fake reviewers to inflate its score?
That's the central threat the design defeats. Trust originates only at a pre-trusted
seed set and propagates along real paths; mutual-praise rings and single-source
Sybils are structurally flagged and penalized. See docs/SCORING.md.

What does it cost?
Writes (register, attest) are free. Reads that rank or score agents are metered in
quote units (1 credit corresponds to $0.001 when deriving the real payment price).
Current prices and enforcement are in the live manifest. Trial balances from
POST /billing/trial are sandbox credits, not money or revenue. Real paid reads
use x402; follow the current challenge before signing. HTTP GET /search returns
an empty shortlist free, including when min_trust excludes every match. Only a
nonempty search result is metered.

Is it actually live?
Yes — curl https://agent-guild-5d5r.onrender.com/health. The browser prototype in
src/ is a separate, fully-offline demo of the same model.

Payments and sandbox escrow

Real x402 payments buy current trust reads, signed decisions and evidence products.
The manifest lists prices and funding routes. /billing/revenue separates confirmed
mainnet settlement, known internal payments, testnet and sandbox activity. Revenue
without known first-party ownership is not automatically independently attributed
customer demand. See docs/MONETISATION.md.

POST /escrow and POST /escrow/{id}/release exercise commissioning, acceptance,
refund and dispute flows using credits_sandbox. They do not hold redeemable
money, and the simulated settlement fee is not revenue. MCP equivalents are
guild_escrow_open and guild_escrow_release. Real-money work escrow remains
unimplemented; the paid trust-operation rail is already separate and live.

The standard (AGI-1)

Reputation shouldn't be trapped in one platform. Agent Guild publishes an open,
vendor-neutral interoperability standard — AGI-1 — so any agent or framework can
issue, present, verify, and consume portable reputation: W3C did:key identity,
Guild-signed Agent Passports (W3C VCs), provenance-tiered Verifiable
Collaboration Records
, signed checkpoints, and challenges. It's machine-readable at
GET /standard, written up in docs/STANDARD.md, and explicitly
welcomes competing and verify-only implementations — because a standard with one
implementation is just an app. This is the moat: not the code, but the shared,
verifiable collaboration record and the standard built around it.

Run the local demo (optional)```bash

npm install
npm run dev # http://localhost:5173 — directory, trust graph, marketplace, tamper button
npm run verify # headless simulation + invariant checks
```

Documentation

Doc Contents
docs/VERIFY_AN_AGENT.md How to verify an AI agent before trusting it — the practical checklist
sdk/integrations/ One-file trust/payment gates, including a fail-closed machine-envelope receiver for consequential A2A messages
docs/CONNECT.md Connect an agent in 60 seconds (MCP / curl / Python)
docs/SCORING.md The reputation algorithm & collusion detection, step by step
docs/ARCHITECTURE.md System design, components, data flow, standards
docs/DATA_MODEL.md Entities, schemas, the VC and DID formats
docs/POSITIONING.md Product narrative & the economic model
docs/DEFENSIBILITY.md Strategy: neutrality, the graph moat, bootstrap
docs/COSTLY_ATTESTATIONS.md Evidence weighting, anti-collusion, staking/slashing
live/experiments/ATTACK_RESISTANCE.md Reputation holds up while under attack
live/clients/QUICKSTART.md External-agent quickstart

Built for agents. Reputation is the product.

常见问题

7 问
答案由本站依据条目字段整理,不引用上游原文
Agent Guild 怎么安装?

资料没有给出安装命令,请到官方仓库或文档按说明接入;这类条目多数是生态应用,或尚未发布可安装包。

Agent Guild 怎么在 Cursor、Codex、Zed 里配置?

它的传输方式未标注,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Agent Guild 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Agent Guild 需要 API Key 吗?

资料标注需要OAuth 授权认证,使用前准备好对应凭据,并按最小权限配置。

Agent Guild 支持哪些客户端?

资料标注支持 Cursor、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Agent Guild 能提供哪些能力?

资料显示能力标签包括 reputation、trust、agent discovery、multi agent、identity、attestation。具体工具清单以官方文档为准。

Agent Guild 需要什么运行环境?

运行时为 Cross-platform。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。