A framework for testing MCP (Model Context Protocol) client and server implementations against the specification.
npm install @modelcontextprotocol/conformanceA framework for testing MCP (Model Context Protocol) client and server implementations against the specification.
> [!WARNING]
> This repository is a work in progress and is unstable. Join the conversation in the #conformance-testing-wg in the MCP Contributors discord.
For SDK maintainers: See SDK Integration Guide for a streamlined guide on integrating conformance tests into your SDK repository.
``bashUsing the everything-client (recommended)
npx @modelcontextprotocol/conformance client --command "tsx examples/clients/typescript/everything-client.ts" --scenario initialize
$3
`bash
Run all server scenarios (default)
npx @modelcontextprotocol/conformance server --url http://localhost:3000/mcpRun a single scenario
npx @modelcontextprotocol/conformance server --url http://localhost:3000/mcp --scenario server-initialize
`$3
`bash
npx @modelcontextprotocol/conformance list
`Overview
The conformance test framework validates MCP implementations by:
For Clients:
1. Starting a test server for the specified scenario
2. Running the client implementation with the test server URL
3. Capturing MCP protocol interactions
4. Running conformance checks against the specification
5. Generating detailed test results
For Servers:
1. Connecting to the running server as an MCP client
2. Sending test requests and capturing responses
3. Running conformance checks against server behavior
4. Generating detailed test results
Usage
$3
`bash
npx @modelcontextprotocol/conformance client --command "" --scenario [options]
`Options:
-
--command - The command to run your MCP client (can include flags)
- --scenario - The test scenario to run (e.g., "initialize")
- --suite - Run a suite of tests in parallel (e.g., "auth")
- --expected-failures - Path to YAML baseline file of known failures (see Expected Failures)
- --timeout - Timeout in milliseconds (default: 30000)
- --verbose - Show verbose outputThe framework appends
as an argument to your command and sets the MCP_CONFORMANCE_SCENARIO environment variable to the scenario name. For scenarios that require additional context (e.g., client credentials), the MCP_CONFORMANCE_CONTEXT environment variable contains a JSON object with scenario-specific data.$3
`bash
npx @modelcontextprotocol/conformance server --url [--scenario ]
`Options:
-
--url - URL of the server to test
- --scenario - Test scenario to run (e.g., "server-initialize"). Runs all available scenarios by default
- --suite - Suite to run: "active" (default), "all", or "pending"
- --expected-failures - Path to YAML baseline file of known failures (see Expected Failures)
- --verbose - Show verbose outputTest Results
Client Testing - Results are saved to
results/:-
checks.json - Array of conformance check results with pass/fail status
- stdout.txt - Client stdout output
- stderr.txt - Client stderr outputServer Testing - Results are saved to
results/server-:-
checks.json - Array of conformance check results with pass/fail statusExpected Failures
SDKs that don't yet pass all conformance tests can specify a baseline of known failures. This allows running conformance tests in CI without failing, while still catching regressions.
Create a YAML file listing expected failures by mode:
`yaml
conformance-baseline.yml
server:
- tools-call-with-progress
- resources-subscribe
client:
- sse-retry
`Then pass it to the CLI:
`bash
npx @modelcontextprotocol/conformance server --url http://localhost:3000/mcp --expected-failures ./conformance-baseline.yml
`Exit code behavior:
| Scenario Result | In Baseline? | Outcome |
| --------------- | ------------ | ----------------------------------------- |
| Fails | Yes | Exit 0 — expected failure |
| Fails | No | Exit 1 — unexpected regression |
| Passes | Yes | Exit 1 — stale baseline, remove the entry |
| Passes | No | Exit 0 — normal pass |
This ensures:
- CI passes when only known failures occur
- CI fails on new regressions (unexpected failures)
- CI fails when a fix lands but the baseline isn't updated (stale entries)
GitHub Action
This repo provides a composite GitHub Action so SDK repos don't need to write their own conformance scripts.
$3
`yaml
steps:
- uses: actions/checkout@v4 # Start your server (SDK-specific)
- run: |
my-server --port 3001 &
timeout 15 bash -c 'until curl -s http://localhost:3001/mcp; do sleep 0.5; done'
- uses: modelcontextprotocol/conformance@v0.1.11
with:
mode: server
url: http://localhost:3001/mcp
expected-failures: ./conformance-baseline.yml # optional
`$3
`yaml
steps:
- uses: actions/checkout@v4 - uses: modelcontextprotocol/conformance@v0.1.11
with:
mode: client
command: 'python tests/conformance/client.py'
expected-failures: ./conformance-baseline.yml # optional
`$3
| Input | Required | Description |
| ------------------- | ----------- | ----------------------------------------------- |
|
mode | Yes | server or client |
| url | Server mode | URL of the server to test |
| command | Client mode | Command to run the client under test |
| expected-failures | No | Path to YAML baseline file |
| suite | No | Test suite to run |
| scenario | No | Run a single scenario by name |
| timeout | No | Timeout in ms for client tests (default: 30000) |
| verbose | No | Show verbose output (default: false) |
| node-version | No | Node.js version (default: 20) |Example Clients
-
examples/clients/typescript/everything-client.ts - Single client that handles all scenarios based on scenario name (recommended)
- examples/clients/typescript/test1.ts - Simple MCP client (for reference)
- examples/clients/typescript/auth-test.ts - Well-behaved OAuth client (for reference)Available Scenarios
$3
- initialize - Tests MCP client initialization handshake
- Validates protocol version
- Validates clientInfo (name and version)
- Validates server response handling
- tools-call - Tests tool invocation
- auth/basic-dcr - Tests OAuth Dynamic Client Registration flow
- auth/basic-metadata-var1 - Tests OAuth with authorization metadata
$3
Run
npx @modelcontextprotocol/conformance list --server to see all available server scenarios, including:- server-initialize - Tests server initialization and capabilities
- tools-list - Tests tool listing endpoint
- tools-call-\* - Various tool invocation scenarios
- resources-\* - Resource management scenarios
- prompts-\* - Prompt management scenarios
Architecture
See
src/runner/DESIGN.md for detailed architecture documentation.$3
- Runner (
src/runner/) - Orchestrates test execution and result generation
- client.ts - Client testing implementation
- server.ts - Server testing implementation
- utils.ts - Shared utilities
- index.ts - Public API exports
- CLI (src/index.ts) - Command-line interface using Commander.js
- Scenarios (src/scenarios/) - Test scenarios with expected behaviors
- Checks (src/checks/) - Conformance validation functions
- Types (src/types.ts) - Shared type definitionsAdding New Scenarios
1. Create a new directory in
src/scenarios/
2. Implement the Scenario interface with start(), stop(), and getChecks()
3. Register the scenario in src/scenarios/index.tsSee
src/scenarios/initialize/` for a reference implementation.