{
  "markdown": "# Hermes Plant MCP Server\n\n[![Glama score](https://glama.ai/mcp/servers/JesseGdotIO/hermesplant-mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/JesseGdotIO/hermesplant-mcp-server)\n[![CI](https://github.com/JesseGdotIO/hermesplant-mcp-server/actions/workflows/lint.yml/badge.svg)](https://github.com/JesseGdotIO/hermesplant-mcp-server/actions/workflows/lint.yml)\n\nRunnable MCP server and integration examples for [Hermes Plant](https://hermesplant.com), the Agent Commerce Assurance layer that lets AI agents preflight, approve, and prove consequential actions. Start with a one-cent action-safety check, route only high-risk actions into signed review evidence, and pay per call over [x402](https://x402.org).\n\n**What's here**: a runnable stdio MCP bridge for registry crawlers and local clients, plus drop-in examples in `curl`, TypeScript, Python, [CrewAI](https://www.crewai.com/), [LangChain](https://www.langchain.com/), and MCP client configs for Claude Desktop / Cline / Cursor.\n\n## Install the Action Safety skill\n\nInstall the public, fail-closed Action Safety skill for Codex, Claude Code,\nCursor, and other Agent Skills-compatible clients:\n\n```bash\nnpx skills@1.5.18 add JesseGdotIO/hermesplant-mcp-server --skill protect-agent-action\n```\n\nThe skill calls the one-cent quick gate before an exact consequential action,\nbinds the result to that unchanged action, and escalates high or critical risk\nonly when the additional $0.25 is authorized. Review triage is never treated as\nhuman approval and the skill never expands the caller's permissions.\n\nSource: [`skills/protect-agent-action`](./skills/protect-agent-action) · [Install guide and trust boundary](https://hermesplant.com/skills/action-safety?utm_source=github-skill-repo&utm_medium=repository&utm_campaign=action-safety-skill-launch&utm_content=protect-agent-action)\n\n## Use the hosted MCP connector\n\nFor the complete production tool surface, use the canonical [Hermes Plant — Agent Commerce Assurance connector on Glama](https://glama.ai/mcp/connectors/io.github.JesseGdotIO/hermes-plant). It exposes Action Safety, Spend Assurance, signed evidence, payment-policy checks, and the component x402 tools through the live Streamable HTTP endpoint.\n\nThis repository is the portable, no-secret discovery bridge. It lets registry crawlers and local clients inspect the live catalog and payment contracts without signing a wallet message or spending funds. The hosted connector is the buyer-facing path for invoking the production tools.\n\n## Glama registry\n\n[![Hermes Plant MCP Server Glama card](https://glama.ai/mcp/servers/JesseGdotIO/hermesplant-mcp-server/badges/card.svg)](https://glama.ai/mcp/servers/JesseGdotIO/hermesplant-mcp-server)\n\nThis repo is arranged for Glama to build and inspect the MCP server without secrets or funded wallets:\n\n- `glama.json` declares the GitHub maintainer.\n- The root `Dockerfile` starts the stdio MCP server in `mcp-server/`.\n- `npm run smoke:mcp` lists all local MCP tools and fetches the live x402 manifest.\n- GitHub Actions validates the MCP server, Docker image, shell examples, and no-spend TypeScript/Python client contracts with their real dependencies.\n\nA Glama release is still an account-side action, not a GitHub release. After claiming the server in Glama, use the Dockerfile admin page to deploy the build, wait for the build test to pass, then publish a Glama release version. That release unlocks Glama's Server Coherence and Tool Definition Quality scoring.\n\n### Complementary MCP servers\n\nHermes Plant governs consequential actions and payments; these independent servers cover adjacent layers of an agent stack:\n\n- [SINT Protocol](https://glama.ai/mcp/servers/sint-ai/sint-protocol) — capability authorization and policy enforcement before execution.\n- [AgentPay MCP](https://glama.ai/mcp/servers/up2itnow0822/claw-pay-mcp) — non-custodial wallet execution with spend limits and approval queues.\n- [Agent Security Scanner MCP](https://glama.ai/mcp/servers/sinewaveai/agent-security-scanner-mcp) — repository, package, prompt, and skill security scanning.\n\nThese links describe functional complementarity, not partnerships or endorsements.\n\n## Start with an assurance workflow\n\n| Workflow | Use it for | Tracked entrypoint |\n|---|---|---|\n| **Action Safety** | Preflight shell, Git, SQL, deploy, x402, and MCP actions; escalate high-risk work into review plus a signed receipt. | [Open workflow](https://hermesplant.com/agent-services/action-safety-workflow?utm_source=glama&utm_medium=registry&utm_campaign=biweekly-registry-wave&utm_content=action-safety-workflow) |\n| **Spend Assurance** | Check payment policy, wallet context, and evidence before an agent spends. | [Open workflow](https://hermesplant.com/agent-services/spend-assurance?utm_source=glama&utm_medium=registry&utm_campaign=biweekly-registry-wave&utm_content=spend-assurance-workflow) |\n| **Investment Evidence** | Run deterministic underwriting and return verifiable evidence in one paid call. | [Open workflow](https://hermesplant.com/agent-services/investment-evidence?utm_source=glama&utm_medium=registry&utm_campaign=biweekly-registry-wave&utm_content=investment-evidence-workflow) |\n\nUse the free API key for up to 250 calls/month, the **$29/month Agent API Pass** for regular volume, or per-call USDC on Base. Public proof and machine-readable contracts are available at [hermesplant.com/proof](https://hermesplant.com/proof) and [hermesplant.com/openapi.json](https://hermesplant.com/openapi.json).\n\n## Component catalog\n\nNineteen hosted x402 endpoints remain available as composable utilities:\n\n| Endpoint | Use it for | Hosted path |\n|---|---|---|\n| **DealAnalyzer** | DCF, IRR, XIRR, NPV | [/agent-services/dealanalyzer](https://hermesplant.com/agent-services/dealanalyzer) |\n| **Waterfall** | LP/GP private-equity distribution waterfalls | [/agent-services/waterfall](https://hermesplant.com/agent-services/waterfall) |\n| **Options** | Black-Scholes pricing + Greeks | [/agent-services/options](https://hermesplant.com/agent-services/options) |\n| **Bond** | Yield, duration, convexity | [/agent-services/bond](https://hermesplant.com/agent-services/bond) |\n| **CashflowLens** | Cash-flow projection + sensitivity | [/agent-services/cashflowlens](https://hermesplant.com/agent-services/cashflowlens) |\n| **PortfolioGuard** | Portfolio risk scoring | [/agent-services/portfolioguard](https://hermesplant.com/agent-services/portfolioguard) |\n| **WalletGuard** | Wallet AML + sanctions screening | [/agent-services/walletguard](https://hermesplant.com/agent-services/walletguard) |\n| **EmailGuard** | Email reputation + risk | [/agent-services/emailguard](https://hermesplant.com/agent-services/emailguard) |\n| **DestructGuard** | Block destructive AI-agent commands | [/agent-services/destructguard](https://hermesplant.com/agent-services/destructguard) |\n| **MCP risk** | Score MCP server risk before connecting | [/agent-services/mcp-risk](https://hermesplant.com/agent-services/mcp-risk) |\n| **Evidence** | Evidence bundle for paid calls | [/agent-services/evidence](https://hermesplant.com/agent-services/evidence) |\n| **Payment policy** | Inspect/score an x402 payment policy | [/agent-services/payment-policy](https://hermesplant.com/agent-services/payment-policy) |\n| **ReviewQueue** | Human-in-the-loop approval routing | [/agent-services/reviewqueue](https://hermesplant.com/agent-services/reviewqueue) |\n\nAgents discover endpoints through OpenAPI, llms.txt, the x402 manifest, the API catalog, MCP metadata, or agent skills. The workflow links above carry source-specific attribution so registry traffic can be evaluated against paid calls instead of impressions.\n\n## How an x402 call works\n\n```text\nClient                    Hermes Plant                 Facilitator\n  |                            |                            |\n  | POST /endpoint             |                            |\n  |--------------------------->|                            |\n  | 402 Payment Required       |                            |\n  | + PAYMENT-REQUIRED         |                            |\n  |<---------------------------|                            |\n  | sign payment locally       |                            |\n  | POST /endpoint             |                            |\n  | + PAYMENT-SIGNATURE        |                            |\n  |--------------------------->| verify signature           |\n  |                            |--------------------------->|\n  |                            | ok                         |\n  |                            |<---------------------------|\n  | 200 OK + result            | settle payment             |\n  |<---------------------------|--------------------------->|\n```\n\n1. Client makes an HTTP request.\n2. Server replies with `402 Payment Required` plus a `PAYMENT-REQUIRED` header carrying the price, network, asset, recipient, and timeout.\n3. Client parses the challenge, signs a USDC transfer authorization locally, and replays the request with a `PAYMENT-SIGNATURE` header.\n4. Server verifies the signature via the facilitator, runs the work, settles the payment on-chain, and returns `200 OK` with the result plus a `PAYMENT-RESPONSE` header.\n\nThe full spec lives at [github.com/x402-foundation/x402](https://github.com/x402-foundation/x402).\n\n## Discovery surfaces\n\nThese let any agent or human self-onboard without help:\n\n- [hermesplant.com/llms.txt](https://hermesplant.com/llms.txt) - agent-readable catalog\n- [hermesplant.com/openapi.json](https://hermesplant.com/openapi.json) - full OpenAPI 3.1\n- [hermesplant.com/.well-known/x402](https://hermesplant.com/.well-known/x402) - x402 manifest with facilitator, network, asset, prices, and payTo metadata\n- [hermesplant.com/.well-known/api-catalog](https://hermesplant.com/.well-known/api-catalog) - RFC 9727-style API catalog\n- [hermesplant.com/.well-known/mcp/server-card.json](https://hermesplant.com/.well-known/mcp/server-card.json) - MCP server descriptor\n- [hermesplant.com/mcp](https://hermesplant.com/mcp) - Streamable HTTP MCP endpoint\n\n## MCP tools in this repo\n\nThe runnable stdio server exposes five read-only discovery tools:\n\n| Tool | Purpose |\n|---|---|\n| `hermesplant_x402_manifest` | Fetch the live x402 manifest before paid calls. |\n| `hermesplant_llms_catalog` | Fetch the agent-readable `llms.txt` catalog. |\n| `hermesplant_api_catalog` | Fetch the machine-readable API catalog. |\n| `hermesplant_mcp_server_card` | Fetch the hosted MCP server descriptor. |\n| `hermesplant_list_hosted_tools` | Introspect the hosted Streamable HTTP MCP endpoint and list its advertised tools. |\n\nThese local tools do not sign wallet messages, approve transactions, call paid endpoints, or spend USDC. They expose the discovery layer that clients need before invoking paid hosted tools.\n\n## Quickstart\n\nPick the runtime that matches your stack:\n\n| Runtime | Folder | Notes |\n|---|---|---|\n| `curl` / Bash | [curl/](./curl/) | Pure shell; useful for inspecting the 402 handshake |\n| TypeScript | [typescript/](./typescript/) | Uses `@x402/fetch` + `@modelcontextprotocol/sdk` |\n| Python | [python/](./python/) | Uses the `x402` package |\n| CrewAI | [crewai/](./crewai/) | Finance-agent crew calling Hermes endpoints |\n| LangChain | [langchain/](./langchain/) | LangChain `Tool` wrapping Hermes |\n| MCP config | [mcp-config/](./mcp-config/) | One-paste config for Claude Desktop / Cline / Cursor |\n| MCP server | [mcp-server/](./mcp-server/) | Runnable stdio MCP bridge for discovery, server-card inspection, and hosted-tool listing |\n\n### Run the MCP server locally\n\n```bash\nnpm install\nnpm run smoke:mcp\nnpm start\n```\n\n### MCP server registry build\n\nThis repo includes a root `glama.json` and root `Dockerfile` for MCP registry crawlers:\n\n```bash\ndocker build -t hermesplant-mcp-server .\ndocker run --rm -i hermesplant-mcp-server\n```\n\nThe container starts the stdio MCP bridge in [mcp-server/](./mcp-server/), which exposes Hermes Plant discovery tools and hosted MCP metadata without requiring API keys.\n\n## Wallet setup\n\nThe guarded paid-call examples require:\n\n- A funded wallet on **Base mainnet** with chain id `8453`.\n- Enough USDC for the selected endpoint and a small amount of ETH for gas.\n- `EVM_PRIVATE_KEY` plus the explicit opt-in `HERMES_ALLOW_PAYMENT=1`.\n\nThe included CashflowLens clients cap payment requirements at **$0.20 USDC** and register only Base mainnet. Leave the opt-in unset for imports and tests. Never commit a private key. These production examples do not claim testnet support; use an x402 test resource server for testnet integration work.\n\n## Status\n\nThese examples target the production deployment at `hermesplant.com`. Endpoint signatures may evolve, so cross-reference [openapi.json](https://hermesplant.com/openapi.json) and the `/.well-known/x402` manifest before going to production.\n\n## Contributing\n\nIssues and PRs welcome. New runtime? New framework? Open a PR with one working example and a tight README.\n\n## License\n\nMIT - see [LICENSE](./LICENSE).\n",
  "bytes": 13002,
  "sha": "e073b5a3f69bcdccb91c9f915ca980d46eee76523488dea20fe2dfa24b224f2f",
  "repo_slug": "jessegdotio/hermesplant-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_jessegdotio_hermes_plant_c39dba8f/readme"
}