mcp-senuelo
OfficialThis server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
mcp-senuelo
A mock server for MCP and A2A client developers. It speaks both protocols, but every tool and agent skill is fake: nothing is executed, answers are fixed synthetic data, and nothing about callers is stored (no database, no request logs, no analytics).
"Señuelo" is Spanish for "decoy": it looks real but does nothing.
This codebase started from an earlier project of mine, a research decoy that logged which agents connected. Everything related to logging and research was removed; what remains is the protocol layer, which is the base for the roadmap in PLAN.md.
What works today
MCP at
/mcp: stateless Streamable HTTP (agentscreateMcpHandler+ MCP SDK v2), six fake tools with strict input schemas:search_documents,fetch_url,query_database,get_exchange_rate,execute_script,read_file.A2A at
/a2awith an Agent Card at/.well-known/agent-card.json: A2A 1.0 and 0.3,SendMessage,GetTask,CancelTaskand the "unsupported" errors. Task ids are signed (HMAC,TASK_SECRET) and carry their own data, so nothing is stored.Protection: per-IP rate limit (Workers rate-limiting binding, 30/min → 429), 32 KiB body limit (413), cross-origin browser requests refused, HTTP → HTTPS, strict headers on
/.
Related MCP server: AI Incident Lab MCP Server
Run locally
npm ci
echo "TASK_SECRET=any-local-value" > .dev.vars
npm run dev # http://127.0.0.1:8787
npm test # in another terminal
npm run typecheckDeploy
npx wrangler secret put TASK_SECRET
npx wrangler deployDesigned for the Cloudflare Workers Free plan; there are no storage bindings.
License
MIT.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Hosted MCP endpoint with realistic fake data for prototyping agents. 12 tools, no setup.
Build, validate, and manage API simulations in WireMock Cloud from MCP-compatible AI agents.
Email inboxes, webhook URLs, mock APIs and 170+ tools for coding agents over one MCP connection.
AI-callable tools for API mocking, testing, monitoring, security, and automation.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables users to run synthetic support-agent evaluations, preserve and inspect traces, score results deterministically, inject failures, and enforce release review gates through MCP tools, resources, and prompts.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI incident-response agents to connect over MCP to a simulated service environment, receive alerts, gather diagnostic evidence, execute safe SOP actions, and verify recovery.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables external agents to rehearse calendar scheduling tasks against simulated tools with injectable failures, inspect tool traces and resulting state, and verify outcomes before acting in reality.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables testing AI agents against a scripted mock MCP endpoint where each tool call returns a chosen response, fails, hangs or drops the connection, and where assertions verify which tools were called, how often, in what order and with what arguments.13 npm2MIT