Agenten stärken
Installation vom Herausgeber. Kein PlugMCP-Endpunkt.
Host a copy with our keys and logs.
Noch kein paketiertes Release in der Registry. Folgen Sie der README des Repositorys.
Remote-URL oder ein Befehl auf Ihrem Rechner? Worin sich die beiden Installationen unterscheiden
Auf PlugMCP ausführen
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
Startenmcp-assert connects to your server exactly like Claude, Cursor, or any MCP client would: real stdio/SSE/HTTP transport, full initialize handshake, actual tool calls. It checks responses against expectations you define in YAML. If it passes mcp-assert, it works with every MCP client.
[!WARNING] We scanned 102 MCP servers and found 4,794 schema issues (2,239 errors) across 55 servers including AWS, Serena, and Grafana. The most common failure: parameters missing type definitions cause agents to send wrong value types. See the scorecard.
Your YAML ──→ mcp-assert ──→ MCP Server
(inputs + assertions) (client) (any language)
│
Pass / Fail
mcp-assert speaks the full MCP protocol: initialize handshake, tools/list discovery, tools/call with real arguments. It finds bugs that unit tests miss because it tests over the wire, not in-process.
The testing standard for MCP, like pytest for Python or Jest for JavaScript.
Add it to any MCP server project in one line:
- uses: blackwell-systems/mcp-assert-action@v1
with:
suite: evals/
[!NOTE] LLMs are for subjective outputs. Assertions are for deterministic ones. Most MCP tools are deterministic. mcp-assert covers them.
# npm (no Go required)
npx @blackwell-systems/mcp-assert
# pip (no Go required)
pip install mcp-assert
# Go
go install github.com/blackwell-systems/mcp-assert/cmd/mcp-assert@latest
# Homebrew
brew install blackwell-systems/tap/mcp-assert
# Docker
docker run blackwellsystems/mcp-assert audit --server "npx my-server"
# Snap (Linux)
sudo snap install mcp-assert --classic
# Scoop (Windows)
scoop bucket add blackwell-systems https://github.com/blackwell-systems/scoop-bucket
scoop install mcp-assert
# Winget (Windows)
winget install BlackwellSystems.mcp-assert
# curl | sh (macOS / Linux)
curl -fsSL https://raw.githubusercontent.com/blackwell-systems/mcp-assert/main/install.sh | sh
Point it at any server:
mcp-assert audit --server "npx my-mcp-server"
Server: my-server
Transport: stdio
Score: 83%
✓ read_query 1ms [E000] responds, returns content
✗ create_table 0ms [E201] internal error: panic: nil pointer...
✓ list_tables 1ms [E000] responds, returns content
3 tools tested, 2 healthy, 1 crashed
Structured error codes classify issues instantly. See Error Reference for all 24 codes.
[!TIP] The audit connects, discovers every tool via
tools/list, calls each one with schema-generated inputs, and reports which tools crash vs. handle errors properly. No YAML needed. To go deeper, generate assertion files and customize them:
# Audit + generate starter YAML for CI
mcp-assert audit --server "npx my-mcp-server" --output evals/
# Edit the generated YAMLs: add expected content, setup steps, multi-step flows
# Run in CI with regression detection
mcp-assert ci --suite evals/ --threshold 95
# Scaffold your first assertion
mcp-assert init evals # Or: init evals --server "my-server" for auto-generation
# Run it
mcp-assert run --suite evals/ --fixture evals/fixtures
See the Getting Started guide for a full walkthrough.
# Vitest
npm install -D @blackwell-systems/vitest-mcp-assert
// mcp.test.ts
import { describeMcpSuite } from '@blackwell-systems/vitest-mcp-assert'
describeMcpSuite('mcp server', 'evals/')
# pytest
pip install pytest-mcp-assert
pytest --mcp-suite evals/
[!IMPORTANT] Same YAML files work across the CLI, Vitest, Jest, Bun, PHPUnit, pytest, and Go test. No migration needed. Write once, run anywhere.
Start with audit (zero setup), then fuzz (adversarial testing), then init (generates everything), then customize the YAML for your specific assertions.
# Generate stub assertions for every tool the server exposes
mcp-assert generate --server "my-mcp-server" --output evals/ --fixture ./fixtures
# Capture actual outputs as snapshots
mcp-assert snapshot --suite evals/ --server "my-mcp-server" --update
# Assert nothing changed
mcp-assert run --suite evals/ --server "my-mcp-server"
Static analysis catches schema issues without executing tools. 24 rules detect problems that cause agents to fail:
mcp-assert lint --server "npx my-mcp-server"
E E103 create_entities Required parameter "entities" has no description
W W114 generate_chart Input schema is 5 levels deep. LLMs struggle with nesting
W W112 (server) Server exposes 27 tools. LLM accuracy degrades beyond 20
5 error(s), 11 warning(s)
Auto-generate fixes:
mcp-assert lint --server "npx my-mcp-server" --fix
memory-server: 9 tools, 25 findings, 23 auto-fixable
E103 create_entities Add description: "The entities value (array)"
W109 search_nodes Add examples to "query": [search term]
W116 read_graph Append: "Returns the graph data as JSON."
23 fixes generated.
Use --strict in CI to fail on warnings:
mcp-assert lint --server "..." --strict --threshold 0
For deterministic tools, mcp-assert is the better fit. For subjective outputs, LLM-as-judge frameworks remain the right choice. Use both if your server mixes tool types.
You'd need MCP protocol bootstrapping, a server-agnostic runner (your Go tests can't test your TypeScript server), and eval features (regression detection, Docker isolation, JUnit output). mcp-assert handles all of that. One YAML file, any server, any language.
Use the mcp-assert GitHub Action for zero-setup CI:
- uses: blackwell-systems/mcp-assert-action@v1
with:
suite: evals/
threshold: 95
Downloads the binary, runs assertions, uploads JUnit XML results, writes GitHub Step Summary. No Go toolchain required on your runners.
Or run directly:
mcp-assert ci --suite evals/ --threshold 95 --junit results.xml
See the CI Integration guide for JUnit XML, markdown summaries, badges, and regression detection.
Run mcp-assert assertions as pytest test items:
pip install pytest-mcp-assert
pytest --mcp-suite evals/
Each YAML file becomes a pytest Item with pass/fail/skip semantics. Configure via pyproject.toml:
[tool.pytest.ini_options]
mcp_suite = "evals/"
mcp_fixture = "fixtures/"
Then just run pytest. See pytest-plugin/README.md for all options.
Run mcp-assert assertions as Vitest tests:
npm install -D @blackwell-systems/vitest-mcp-assert
Auto-discover all YAML files in a directory:
// mcp.test.ts
import { describeMcpSuite } from '@blackwell-systems/vitest-mcp-assert'
describeMcpSuite('mcp server', 'evals/')
Or run individual assertions:
import { test } from 'vitest'
import { runMcpAssert } from '@blackwell-systems/vitest-mcp-assert'
test('echo tool', () => runMcpAssert('evals/echo.yaml'))
Same YAML files work across Vitest, pytest, and the CLI. See vitest-plugin/README.md for all options.
Full documentation is available at blackwell-systems.github.io/mcp-assert:
MIT
The testing standard for MCP servers. Lint (14 rules), test, and fuzz over real stdio/SSE/HTTP transport. 18 assertion types in YAML. Found 4,794 schema issues across 55 servers. Any language, no mock
Übersicht
The testing standard for MCP servers. Lint (14 rules), test, and fuzz over real stdio/SSE/HTTP transport. 18 assertion types in YAML. Found 4,794 schema issues across 55 servers. Any language, no mocks, single binary.
Tools
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
MCP Assert läuft lokal über stdio.
Zuletzt geprüft: 2026-11-13. The testing standard for MCP servers. Lint (14 rules), test, and fuzz over real stdio/SSE/HTTP transport. 18 assertion types in YAML. Found 4,794 schema issues across 55 servers. Any language, no mocks, single binary.