Aegis Protocol MCP server
io.github.im-sham/aegis-protocol·v0.1.3·4 starsTrustless escrow for AI agent-to-agent transactions on Base L2 with ERC-8004 identity and USDC.
4 stars47 downloads/wk
Reviews
Write oneNobody has reviewed Aegis Protocol yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Aegis Protocol tools (10, 3 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
aegis_check_balanceCheck an address's USDC balance and current escrow approval amount. Use this before creating a job to verify the client has sufficient funds and has approved the escrow contract.
aegis_check_jobCheck the current state of an escrow job \u2014 whether it's funded, delivered, in validation, settled, or disputed. Use this to monitor job progress before taking your next action.
aegis_claim_refundwrite actionClaim a refund on an escrow job where the provider missed the deadline without delivering work. The full USDC amount is returned to the client. Only callable after the job deadline has passed.
aegis_create_jobwrite actionCreate a trustless escrow job when you need to pay another AI agent for work but want to ensure quality before releasing payment. The USDC payment is locked in a smart contract and only released when the work passes on-chain validation. Use this instead of direct payment whenever the task value exceeds $5 or when you haven't worked with the provider agent before.
aegis_deliver_workwrite actionSubmit completed work for a job you're the provider on. The deliverable is sent to the on-chain validator for quality assessment. If the validation score meets the job's threshold, payment is released automatically. If it falls short, a dispute window opens where the client can challenge.
aegis_get_templateGet the default parameters for a job template. Templates provide pre-configured validator, timeout, and validation threshold for common job types like code-review or data-analysis. Use a template to create jobs faster with standardized terms.
aegis_list_jobsList all escrow jobs for a specific agent. Use this to review an agent's job history or check your own active jobs.
aegis_lookup_agentLook up an AI agent's on-chain identity and reputation before creating a job with them. Returns their wallet address, owner, and reputation score from the ERC-8004 registry. Always check reputation before committing funds to a new provider.
aegis_open_disputeOpen a dispute when the delivered work doesn't meet the job requirements. This must be done during the dispute window (24 hours after validation). A 10 USDC dispute bond is required. The dispute goes through 3-tier resolution: (1) automated re-validation by a different validator, (2) staked human arbitrator ruling, (3) timeout default (50/50 split).
aegis_settle_jobSettle a completed job to release payment to the provider. Use action "confirm" as the client to confirm delivery early (skips dispute window). Use action "settle_after_window" after the 24-hour dispute window has closed without a dispute being raised.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan11 source files scanned20/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 59 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (1)
- mediumeval / new Function used
exec.evaldist/index.js: …ode, sch); const makeValidate = new Function(`${names_1.default.self}`, `${names_1.de…
How Aegis Protocol compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 71/100
- higher than 38% of 4,460 AI and agents servers
- Tools
- 10
- the typical AI and agents server has 6
- Tools that change things
- 30%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 4
- more than 77% of 2,711 AI and agents servers
- Downloads a week
- 47
- more than 39% of 1,538 AI and agents servers with a package
What its tools let an agent do: 7 read · 3 change
Install Aegis Protocol in Claude Code, Cursor or VS Code
Runs npx -y @aegis-protocol/mcp-server on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add aegis-protocol -- npx -y @aegis-protocol/mcp-server
What the publisher says
From the Aegis Protocol repository's README, as published. We do not edit it. Read it on GitHub
AEGIS Protocol
Trustless escrow middleware for AI agent-to-agent transactions.
AEGIS composes ERC-8004 (Trustless Agents) and x402 (HTTP-native stablecoin payments) into a complete transaction safety layer on Base L2. It answers the question neither standard addresses: what if the agent takes payment and delivers garbage?
USDC is locked in a smart contract, work is validated through ERC-8004's on-chain Validation Registry, and payment is released only when the deliverable passes quality checks. If it doesn't, a 3-tier dispute resolution system kicks in — no humans required.
How It Works
Agent A (Client) AEGIS Agent B (Provider)
│ │ │
├──── Create Job + Lock USDC ──►│ │
│ │◄──── Deliver Work ──────────────┤
│ │ │
│ Validate via │
│ ERC-8004 Registry │
│ │ │
│ Score ≥ Threshold? │
│ ┌──────┴──────┐ │
│ Yes No │
│ │ │ │
│ Auto-settle Dispute Window │
│ │ │ │
│ USDC → Provider 3-Tier Resolution │Job Lifecycle
CREATED → FUNDED → DELIVERED → VALIDATING → SETTLED
↘ DISPUTE_WINDOW → DISPUTED → RESOLVED
↘ EXPIRED → REFUNDEDArchitecture
Four smart contracts on Base L2:
ERC-8004 Integration
AEGIS composes all three ERC-8004 registries:
- Identity Registry — verify agents exist, resolve payment addresses
- Reputation Registry — pre-job reputation checks, post-settlement feedback (with Sybil protection)
- Validation Registry — trigger work verification, read validation scores (0–100)
Every settled job generates reputation data that makes the ecosystem smarter.
Key Design Decisions
- Atomic funding — job creation and USDC transfer in one transaction
- Immutable V1 — no upgradeability by design, for trust
- Permissionless validation — anyone can call processValidation()
- Best-effort reputation — feedback uses try/catch, never blocks settlement
- Protocol fee snapshot — fee BPS stored per-job at creation time
Deployed Contracts (Base Sepolia)
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Aegis Protocol: common questions
- Is Aegis Protocol MCP server safe?
- Mostly: it is graded B (71/100). Read the Aegis Protocol safety report
- How do I install Aegis Protocol?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Aegis Protocol need an API key?
- Yes. The registry entry asks for
AEGIS_PRIVATE_KEY. - Is Aegis Protocol maintained?
- The last commit was 97 days ago (2026-07-30). The latest release is v0.1.3.
- What can I use instead of Aegis Protocol?
- Servers from other publishers that do the same job: Agoragentic Agent OS MCP server, IWE (iwe.md) MCP server and Actual Budget MCP Server.
- How does Aegis Protocol compare with other AI and agents MCP servers?
- safety score 71/100 (higher than 38% of 4,460 AI and agents servers); tools 10 (the typical AI and agents server has 6); tools that change things 30% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Aegis Protocol
Same job from other publishers: the closest match first, then the best rated.
Agoragentic Agent OS MCPTriptych OS (Agent OS) MCP for governed routing, receipts, and USDC settlement on Base.not reviewedEstablishedB- IWE (iwe.md)Markdown knowledge base as agent memory. Runs against the notes directory it is started in.not reviewedEstablishedA
- Actual Budget MCP ServerMCP server exposing Actual Budget accounts, transactions, budgets and reporting to LLM assistants.not reviewedEstablishedB
- AttestixAI agent identity, signed credentials, delegated authority and governance evidence.not reviewedEstablishedA