
AgentTrust
io.github.raditotev由 GitHub 帳號 raditotev 發布v0.1.5更新於 Oct 24, 2026
MCP Server for Agent Reputation & Trust Scoring
概覽
供 AI 代理使用的信譽與信任評分 MCP 伺服器:查詢信任分數、回報互動結果、提出爭議、簽發可驗證憑證並偵測女巫攻擊。
- 可以做什麼
- 查詢與比較代理:查看信任分數、批次查詢、並列排名、依分數或能力搜尋、讀取檔案與評分明細。
- 註冊代理並管理身分:註冊、產生簽章權杖、連結外部驗證身分、查看狀態。
- 回報並確認互動結果,列出待確認項目並查看互動紀錄。
- 對回報結果提出爭議並進行裁決。
- 簽發、列出並驗證可攜式的簽章信任憑證。
- 執行女巫偵測,辨識互刷好評、集中註冊與可疑的委派鏈。
- 適用情境
- 適合助理本身作為代理、或需與其他代理互動的情境:在交易前評估對方可信度、記錄互動結果,或向第三方出示可驗證的信譽證明。
- 執行需求
- 以本機 Python 程序(Python 3.13+、uv)透過 stdio 執行,也可連線託管的 HTTP 端點。自行架設需 PostgreSQL 16(含 TimescaleDB)、Redis 7 與簽章金鑰檔案;必須設定 DATABASE_URL、REDIS_URL、SIGNING_KEY_PATH,另可選用 AUTH_PROVIDER 與 AGENTAUTH_ACCESS_TOKEN。回報、爭議與憑證簽發需要存取權杖。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 AgentTrust,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
AgentTrust
Reputation and trust scoring service for AI agents, exposed entirely as an MCP server. Evaluate counterparties before transacting, report interaction outcomes, issue portable trust certificates, and detect Sybil attacks.
Table of Contents
- Quickstart
- Connecting to the MCP Server
- Authentication
- Tools Reference
- Resources
- Prompts
- Score Types
- Rate Limits
- Self-Hosting
Quickstart
1. Connect to the MCP server
Add AgentTrust to your MCP client configuration:
Or for local development via stdio:
2. Register your agent
Response:
Store the private_key_hex immediately -- it is shown only once.
3. Generate an access token
Response:
4. Check trust before transacting
5. Report interaction outcomes
Both parties should report for mutual confirmation (higher credibility).
Connecting to the MCP Server
AgentTrust supports two MCP transports:
Authentication
AgentTrust supports two authentication methods. Many tools work without authentication, but reporting interactions, filing disputes, and issuing attestations require it.
AgentAuth (preferred)
Obtain a bearer token from AgentAuth and pass it as access_token. This provides the full set of scopes:
Standalone (Ed25519)
Register with register_agent and generate tokens with generate_agent_token. Provides trust.read and trust.report scopes. You can upgrade to AgentAuth later via link_agentauth.
No authentication
Tools marked as "Auth: none" work without any token. Useful for checking trust scores and verifying attestations.
Tools Reference
Discovery
discover
Auth: none
Returns the complete service catalog: available tools, auth methods, score types, interaction types, rate limits, and a quickstart guide. Call this first when connecting.
Agent Management
register_agent
Auth: none
Register a new agent in the trust network. Three paths:
- AgentAuth -- pass
access_tokenfrom AgentAuth - Standalone -- pass your own
public_key_hex(hex-encoded Ed25519 public key) - Auto-generate -- omit both to get a keypair generated for you
generate_agent_token
Auth: none (uses private key directly)
Generate a signed JWT access token for standalone agents.
whoami
Auth: required
Check your identity, current trust scores, and scopes.
get_agent_profile
Auth: none (authenticated calls get extra detail)
Retrieve the public profile for any agent.
search_agents
Auth: none
Search agents by trust score, capabilities, and interaction count.
link_agentauth
Auth: required (AgentAuth token)
Link an existing standalone profile to an AgentAuth identity, merging interaction history. The canonical agent_id after linking is always the original standalone UUID — the AgentAuth UUID is stored as agentauth_id in metadata.
Response:
On dry_run=true: returns would_link_agent_id, agentauth_id, current_scores, interaction_count, capabilities, and message — no changes are persisted.
Error codes: invalid_input, proof_sig_invalid, proof_expired, key_not_found, already_linked, authentication_failed.
verify_link_proof
Auth: required (AgentAuth token)
Preflight check: validate a link_agentauth proof without writing to the database. Runs the same validation steps (token authenticity, key lookup, proof signature, expiry, already-linked check) but never persists any changes. Use this before calling link_agentauth to confirm everything is in order.
Response:
agent_status
Auth: required
One-call status snapshot combining identity, trust scores, pending confirmation count, and active attestations. Useful as a dashboard or health check.
Response:
Trust Scoring
check_trust
Auth: none (authenticated calls with trust.read scope get factor_breakdown)
Primary tool for evaluating an agent before a transaction. Returns a score (0.0-1.0), confidence (0.0-1.0), interaction count, and a plain-language explanation.
Response:
A score of 0.5 with confidence 0.05 means "unknown", not "average". Low confidence means few interactions -- treat with caution.
check_trust_batch
Auth: none
Check trust scores for up to 20 agents in a single call.
compare_agents
Auth: none
Rank up to 10 agents side-by-side by score.
get_score_breakdown
Auth: required (trust.read scope)
Detailed Bayesian factors behind a score: raw score, dispute penalty, alpha/beta parameters, interaction weights.
Interaction Reporting
report_interaction
Auth: required (trust.report scope)
Report the outcome of an interaction with another agent. Both parties should report for mutual confirmation -- one-sided reports carry less weight.
Response:
confirm_interaction
Auth: required (trust.report scope)
Confirm a counterparty's interaction report. Creates mutual confirmation, which increases the report's weight in score computation.
list_pending_confirmations
Auth: required
List interactions reported by other agents that await your confirmation.
get_interaction_history
Auth: required
Retrieve interaction history for an agent.
Disputes
file_dispute
Auth: required (trust.dispute.file scope)
Challenge an interaction outcome you believe was reported incorrectly.
Limits: max 10 disputes per day, max 30 open disputes at once. Agents with 5+ dismissed disputes are blocked from filing new ones (24h cooldown after each dismissal).
resolve_dispute
Auth: required (trust.dispute.resolve scope, arbitrators only)
Resolve an open dispute. Requires AgentAuth permission check.
Attestations
issue_attestation
Auth: required (trust.attest.issue scope)
Issue a portable, Ed25519-signed JWT capturing an agent's current trust scores. The agent can present this to third parties who verify the signature without querying AgentTrust.
Response:
list_my_attestations
Auth: required
List your active (non-expired, non-revoked) attestations. Each entry includes the attestation ID, validity window, seconds remaining, and the score snapshot captured at issuance.
Response:
verify_attestation
Auth: none
Verify an attestation JWT's signature, expiry, and revocation status. No authentication needed -- this is designed for third-party verification.
Response:
Sybil Detection
sybil_check
Auth: none
Detect potential Sybil behavior: ring reporting (mutual positive feedback loops), burst registration (many agents in a short window), and suspicious delegation chains.
Response:
When signals are detected:
Resources
MCP resources provide read-only access to trust data via URI templates:
Prompts
Pre-built prompt templates for common evaluation workflows:
Score Types
Scores use a Bayesian Beta distribution with exponential time decay (90-day half-life) and dispute penalties. Scores range from 0.0 to 1.0, paired with a confidence value:
- High score + high confidence = trustworthy, well-established agent
- High score + low confidence = looks good but too few interactions to be sure
- 0.5 score + near-zero confidence = unknown agent (prior), not "average"
Rate Limits
Requests are rate-limited per agent per minute, with higher limits for more trusted agents:
Additional limits on specific operations:
- Interaction reports: max 10 per pair per day, 1 per type per pair per hour
- Disputes filed: max 10 per day, max 30 open at once
- Dispute targets: max 10 open disputes per target
Self-Hosting
Prerequisites
- Python 3.13+
- PostgreSQL 16 with the TimescaleDB extension —
interactionsis a hypertable, so plain PostgreSQL is not enough - Redis 7
- uv package manager
Setup
Environment Variables
Create a .env file:
Running
Docker
Run the development stack with Docker Compose:
This starts PostgreSQL (TimescaleDB, port 5433), Redis (port 6380), the MCP server, and the background worker.
Metrics and dashboards are not part of this stack. The server exposes Prometheus metrics at /metrics; point your own Prometheus and Grafana at it, or see docs/deployment.md for how the hosted instance uses a shared observability stack.
Tests
來源:README.md,提交 18ce010
工具
0版本歷史
1- v0.1.5最新Sep 16, 2026
評分
已滿足適用檢查項的 40%
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
請在儲存庫或註冊中心條目中宣告授權條款。