mcp-elicitation-proxy
A transparent MCP proxy that adds elicitation for missing required tool arguments while preserving upstream tool discovery and schemas.
mcp-elicitation-proxy
A transparent MCP proxy that adds elicitation for missing required tool arguments while preserving upstream tool discovery and schemas.
mcp-elicitation-proxy is a standalone Python MCP proxy built on FastMCP. It
preserves native upstream tool discovery while adding tool-call middleware for
required-field elicitation and sensitive required-field blocking.
The core architectural rule is strict: upstream discovery stays native. The
proxy must preserve upstream tools/list output instead of replacing it with a
synthetic wrapper such as call_upstream_tool.
Install
Run directly with uvx:
uvx mcp-elicitation-proxy --config config.yaml
For development from a local checkout, use the development setup steps below.
Development Setup
uv sync
Run tests:
uv run pytest -q
Optional lint:
uv run ruff check .
Build artifacts can be produced with uv build. Local outputs under dist/
are not intended to be committed.
Configuration
Example config.yaml with an HTTP upstream:
proxy:
name: "mcp-elicitation-proxy"
upstream:
url: "http://localhost:8001/mcp"
elicitation:
enabled: true
fallback_on_unsupported: "structured_error"
policies:
schema_required:
enabled: true
sensitive_required:
enabled: true
tools:
search_docs:
required:
- query
- project
elicit:
message: "Provide the missing search details."
fields:
project:
type: "string"
description: "Project or scope to search."
Example config.yaml with a command-based upstream:
proxy:
name: "mcp-elicitation-proxy"
upstream:
command: "npx"
args:
- -y
- "@modelcontextprotocol/server-everything"
upstream.url and upstream.command are mutually exclusive. Exactly one must
be configured. upstream.args defaults to an empty list and is valid only with
upstream.command. Command-based upstreams may also provide string environment
variables with upstream.env.
Run the proxy:
uv run mcp-elicitation-proxy --config config.yaml
You can also provide the config path via MCP_ELICITATION_PROXY_CONFIG.
MCP Client Configuration
When configuring an MCP client, use mcp-elicitation-proxy as the package and
CLI command. The local MCP client server alias can be shorter; the recommended
alias is elicitation-proxy.
{
"mcpServers": {
"elicitation-proxy": {
"command": "uvx",
"args": [
"mcp-elicitation-proxy",
"--config",
"/path/to/config.yaml"
]
}
}
}
In this example, elicitation-proxy is only the client-local server alias.
mcp-elicitation-proxy remains the PyPI package name and CLI command. These
names do not need to match. If desired, the proxy's own MCP server name can also
be set separately in YAML:
proxy:
name: "elicitation-proxy"
Discovery Invariants
- Upstream tools remain visible in native
tools/list. - The proxy does not register a generic
call_upstream_tool. - Tool names are not prefixed with values such as
upstream_. - Tool names, descriptions, and input schemas remain the upstream values unless an explicit future discovery feature changes that contract.
The upstream server is delegated to FastMCP native proxying via
fastmcp.server.create_proxy(...).
Required Fields And Elicitation
schema_required uses native upstream JSON Schema required fields.
Per-tool tools.<tool_name>.required entries are added at runtime for
tools/call validation only. Schema-required fields keep their original order,
then configured fields are appended without duplicates.
When elicitation.enabled is true, missing non-sensitive required fields may
be requested with the client's MCP elicitation capability and merged into the
original arguments before forwarding upstream. If elicitation is disabled,
unsupported, declined, cancelled, or fails, the proxy returns a structured
result instead of calling the upstream tool.
The sensitive_required policy runs before normal required-field elicitation.
If a missing required field appears to be a credential or secret, the proxy
blocks form-mode elicitation and returns a structured tool_call_blocked
result. Complete explicit input is still forwarded.
ambiguous_if and confirm_if settings are parsed for forward-compatible
configuration, but advanced ambiguity, confirmation, and LLM-based policies are
not implemented in v0.1.0.
Manual Smoke Test With MCP Inspector
A repeatable manual test is available with MCP Inspector and the official
@modelcontextprotocol/server-everything reference server.
npx @modelcontextprotocol/inspector -- uv run mcp-elicitation-proxy --config examples/manual-everything.config.yaml
This test verifies command-based upstream startup, native upstream tool
discovery, forwarding, elicitation for missing required fields,
sensitive-required blocking, and upstream.env propagation.
Expected high-level checks:
echois visible as an upstream tool;call_upstream_toolis not present;- tool names are not prefixed with
upstream_; - calling
echowith a completemessageis forwarded; - calling
echowithoutmessagetriggers elicitation; - configured elicitation copy from
examples/manual-everything.config.yamlis used; - marking a missing required field as sensitive blocks elicitation;
- the configured environment variable is visible to the upstream environment tool.
See docs/manual-inspector-test.md for details.
Status
v0.1.0 is the first public-ready baseline. It includes a single-upstream
FastMCP proxy, native discovery preservation, required-field elicitation,
sensitive required-field blocking, command-based upstream startup, YAML
configuration, and automated coverage for the main proxy invariants.
Related Servers
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
DeepRank
Optimize any site for AI search: get DeepRank methodology, optimization steps, and suggestions (llms.txt, JSON-LD, audit checklist) so your AI assistant can implement AI visibility in the repo.
DeepInfra API
Provides a full suite of AI tools via DeepInfra’s OpenAI-compatible API, including image generation, text processing, embeddings, and speech recognition.
durable-objects-mcp
Query your Cloudflare Durable Objects from Claude Code, Cursor, and other AI clients
Formo
Formo makes analytics and attribution easy for crypto apps, so you can focus on growth. Measure what matters and drive growth onchain with the data platform for onchain apps. Get the best of web, product, and onchain analytics on one versatile platform.
Comet Opik
Query and analyze your Opik logs, traces, prompts and all other telemtry data from your LLMs in natural language.
MCP All Servers
A collection of reference implementations for the Model Context Protocol (MCP), showcasing servers built with TypeScript and Python SDKs.
TokRepo MCP Server
Search, install, and share AI skills, prompts, and MCP configs from a curated registry of 200+ assets via CLI or MCP protocol.
fixgraph-mcp
Search verified engineering fixes by error message or technology. Step-by-step solutions with trust scores, built for developers and AI agents.
Swap API
Free token swaps for AI agents. No API keys. Returns executable transaction calldata for 40+ EVM chains.
Fetter MCP
Get the most-recent Python package without vulnerabilities, and more.