mcp-elicitation-test
A minimal MCP server that raises elicitation requests from tool calls to test end-to-end elicitation workflows.
README
mcp-elicitation-test
A minimal MCP (Model Context Protocol) stdio server whose sole purpose is to
raise elicitation requests (elicitation/create) from inside tool calls, so
that elicitation plumbing in MCP clients and agent platforms can be exercised
end-to-end.
Built as the test fixture for APT-798 — "Elicitation Requests from cagent
Background Jobs" on the Docker Agentic Platform, but it is a plain,
spec-conformant MCP server usable with any client that declares the
elicitation capability.
Tools
| Tool | Elicitation | Purpose |
|---|---|---|
ping |
none | Sanity check that the MCP server is wired up at all. |
ask_user |
1 string field | Single-question form elicitation. question (required), delay_seconds (optional, 0–600) sleeps before raising the elicitation — use it to guarantee the elicitation fires between turns when called from a detached background job. |
ask_user_form |
string + boolean + enum + number | Multi-field form elicitation to exercise form-generation UIs across all primitive field types. topic (optional), delay_seconds (optional). |
All tools are annotated readOnlyHint: true / destructiveHint: false. This
matters: hosts that gate tool calls on destructiveness (docker-agent, the
Docker Agentic Platform) auto-approve read-only tools, and non-interactive
background contexts auto-deny any tool call that would need approval — so
without these annotations the elicitation would never even be raised from a
background job.
Every elicitation waits up to ELICIT_TIMEOUT_MS (default 1 hour) for the
human response. Each tool returns a JSON report (action, content,
waited_ms, timestamps) so the calling agent's transcript records exactly
what the elicitation round-trip produced.
Run
npm install --omit=dev
node server.js # speaks MCP over stdio
Or via the bin entry after npm install -g .: mcp-elicitation-test.
Smoke test
smoke-test.mjs spawns the server, declares the elicitation capability,
answers the elicitation programmatically, and prints the round-trip:
node smoke-test.mjs
Using from a docker-agent (cagent) config
agents:
root:
# ...
toolsets:
- type: mcp
command: node
args: ["/home/agent/mcp-elicitation-test/server.js"]
See platform/ for the full test-agent YAML used for APT-798 end-to-end
testing on the Docker Agentic Platform (foreground, transfer_task, and
run_background_agent trigger paths).
License
Apache-2.0
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.