Skip to main content
Glama
QWED-MCP

QWED-MCP

Official
by QWED-AI

PyPI Docker Verified Docker Scout Cloudflare Snyk Security Docs by Mintlify Deploys by Netlify License MCP GitHub stars Verified by QWED

MCP Server for QWED Verification — Bring deterministic verification to Claude Desktop, VS Code, and any MCP-compatible AI assistant.

šŸ“š Full Documentation: docs.qwedai.tech/mcp


⚔ Quick Install

pip install qwed-mcp

Related MCP server: SymPy Sandbox MCP

šŸš€ Setup with Claude Desktop

Step 1: Find your config file

OS

Path

Windows

%APPDATA%\Claude\claude_desktop_config.json

macOS

~/Library/Application Support/Claude/claude_desktop_config.json

Linux

~/.config/Claude/claude_desktop_config.json

Step 2: Add QWED-MCP

macOS/Linux:

{
  "mcpServers": {
    "qwed-verification": {
      "command": "qwed-mcp"
    }
  }
}

Windows (use python -m):

{
  "mcpServers": {
    "qwed-verification": {
      "command": "python",
      "args": ["-m", "qwed_mcp.server"]
    }
  }
}

Step 3: Restart Claude Desktop

Quit completely (system tray → Quit) and reopen.

Step 4: Test it!

Ask Claude:

"Write a python script that verifies a 10,000 investment at 7.5% for 5 years using the qwed_new math engine, and run it using execute_python_code."


āš ļø Migration Note: Deprecation of verify_* Tools

To solve "context bloat" and align with the new MCP standard (RFC-9728), all 1:1 functional tools (e.g., verify_math, verify_sql, verify_code) have been removed as of v0.2.1.

They have been replaced with a single, highly capable tool: šŸ‘‰ execute_python_code

Before:

"Use verify_math to check this formula." (Claude loads 14 different tool schemas into context)

After:

"Use execute_python_code to write and run a script that imports qwed_new.engines.math_engine to verify..." (Claude loads 1 tool schema into context)

If you see an "Unknown tool" error, it means Claude is trying to use a legacy tool. Simply tell Claude: "The verify_* tools are removed. Use execute_python_code to natively write and run a Python verification script."


šŸ”§ Available Tools

Tool

Description

Use Case

execute_python_code

Subprocess Execution

The single entrypoint for all QWED capabilities. Executes dynamically generated Python code in a subprocess with restricted environment variables. Note: Runs with server privileges; ensure inputs are trusted.


šŸ’” Example Prompts for Claude

Note: Claude already knows how to use QWED natively via standard Python imports.

Financial Calculations

A bank says: "Invest $10,000 at 7.5% compounded quarterly for 5 years = $14,356.29"
Please write a short Python script using the standard compound interest formula to verify this, and run it with execute_python_code.

Loan EMI Verification

Verify: ₹10,00,000 loan at 9% for 5 years = EMI of ₹20,758
Write a python script importing necessary tools to verify this EMI calculation, and execute it using execute_python_code.

Complex Reasoning Workflows (The Power of Python)

Read the user terms in the attached document. 
1. Use execute_python_code to extract and verify the legal clauses using qwed_legal.
2. In the same script, verify if the referenced financial penalties align with the allowed boundaries.

šŸ—ļø How It Works

ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”
│      Claude Desktop / VS Code             │
│           (MCP Client)                    │
ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¬ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜
                  │ MCP Protocol (JSON-RPC)
                  ā–¼
ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”
│           QWED-MCP Server                 │
ā”œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¤
│ execute_python_code()                     │
│  └─► Subprocess Execution (Restricted Env)│
│       └─► Native QWED library execution   │
ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜

šŸŽÆ Why QWED-MCP?

Note: Subprocess execution provides answers/checks purely based on what QWED SDK methods are invoked inside the executed scripts. Execution itself does not guarantee injection detection without specific SDK calls.

Without QWED-MCP

With QWED-MCP

LLM calculates → 95% correct

Executes Python script calling qwed_finance → 100% correct

LLM writes SQL → might inject

Script uses qwed_new analyzer → injection detected

LLM reasons → might be wrong

Z3 solver executed via SDK → formally proven

LLM codes → might be unsafe

AST check script executed → security checked


šŸ’” What QWED-MCP Is (and Isn't)

āœ… QWED-MCP IS:

  • MCP Server that adds verification tools to Claude Desktop and VS Code

  • Deterministic — uses SymPy (math), Z3 (logic), AST (code) for exact verification

  • Open source — works with any MCP-compatible AI assistant

  • A safety layer — catches LLM hallucinations in real-time

āŒ QWED-MCP is NOT:

  • A replacement for Claude — it enhances Claude with verification tools

  • A chatbot — it's a backend server that Claude calls

  • Internet-connected — all verification happens locally

  • A fine-tuned model — uses symbolic engines, not ML

Think of QWED-MCP as giving Claude a "calculator" for math and a "theorem prover" for logic.

Claude reasons. QWED-MCP verifies.


šŸ†š How We're Different from Other MCP Servers

Aspect

Other MCP Servers

QWED-MCP

Purpose

Connect to APIs, databases, files

Verify LLM outputs

Approach

Fetch external data

Compute deterministic proofs

Engines

API wrappers

SymPy, Z3, AST analyzers

Accuracy

Depends on data source

100% mathematically proven

Offline

Often need internet

Fully local, no APIs

With Claude Desktop

ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”     ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”     ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”
│      Claude       │     │       QWED-MCP        │     │  Verified Answer  │
│ "What's d/dx x³?" │ ──► │ execute_python_code() │ ──► │      "3x²" āœ“      │
│ "Write script to  │     │ Runs SymPy natively   │     │ (STDOUT Captured) │
│ check."           │     ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜     ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜
ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜

šŸ”’ Security & Privacy

All verification happens locally. Nothing is sent to external servers.

Concern

QWED-MCP Approach

Data Transmission

āŒ No external API calls

Storage

āŒ Nothing logged or stored

Dependencies

āœ… Local engines (SymPy, Z3)

Code Analysis

āœ… Your code never leaves your machine

Perfect for:

  • Enterprises with strict security policies

  • Air-gapped development environments

  • Sensitive code review workflows


ā“ FAQ

Yes! Open source under Apache 2.0. Use it commercially, modify it, distribute it.

QWED-MCP works with any MCP-compatible client. VS Code with Claude extension supports MCP, so yes!

No. QWED-MCP runs entirely locally. No API keys, no cloud calls.

QWED-Core is the Python library. QWED-MCP wraps it as an MCP server so Claude can use it as a tool.

Yes! The server is extensible. Fork it and add your custom @mcp.tool() functions.


šŸ—ŗļø Roadmap

āœ… Released (v0.2.3)

  • Context bloat resolution (RFC-9728 compatibility)

  • Unified execute_python_code environment

  • Secure process isolation (env-restricted) and robust timeouts

  • Claude Desktop integration

  • Windows/macOS/Linux support

  • Hardened math sandbox: AST allowlist for expression evaluation (GHSA-2p69-jpm6-jrxh)

  • qwedai.com removed from the trusted skill source domains (#71)

  • Requires mcp>=1.30.0,<2. MCP SDK 1.30.0 patches GHSA-84m7-p3x7-pcfv, GHSA-rwrf-2pqf-9j8j and GHSA-5h93-6whr-6q8j; for GHSA-w4fh-qvv9-3v23, HTTP servers that use the SDK's bearer authentication must also set validate_token_resource=True. qwed-mcp runs over stdio and uses neither the HTTP transports nor bearer authentication. MCP SDK 2.x removed the server API qwed-mcp uses

  • Reports its own version to MCP clients during initialisation

🚧 In Progress

  • verify_json — JSON Schema validation tool

  • verify_finance — NPV/IRR/amortization tool

  • Cursor IDE integration guide

šŸ”® Planned

  • verify_legal — Deadline and liability verification

  • verify_statistics — Hypothesis test validation

  • SSE (Server-Sent Events) transport for web UIs

  • TypeScript implementation


šŸ“ Examples

See the examples/ folder for:

  • Python client usage

  • Sample verification scripts

  • Integration examples


šŸ› ļø Development

# Clone
git clone https://github.com/QWED-AI/qwed-mcp.git
cd qwed-mcp

# Install with dev dependencies
pip install -e ".[dev]"

# Run tests
pytest tests/ -v

# Format code
black src/

šŸ“– Documentation



šŸ“„ License

Apache 2.0 — See LICENSE


Available Tools

2 tools
execute_python_codeA

Executes Python code in a subprocess with restricted environment variables. Note: This runs with server privileges; ensure inputs are trusted.

Inputs: code (required), background.

verification_statusB

Check the execution status and output of a background verification task.

Inputs: job_id (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: one executes Python code, the other checks the status of a background task. There is no overlap in functionality.

    Naming Consistency4/5

    Both tools use snake_case, but one follows a verb_noun pattern (execute_python_code) while the other is noun_noun (verification_status). Slight inconsistency but still readable.

    Tool Count2/5

    With only 2 tools, the server feels very sparse for any meaningful functionality. A code execution server would typically need more tools for environment management, file I/O, etc.

    Completeness2/5

    The tool set lacks essential operations for a code execution server, such as managing environments, reading files, or handling dependencies. Only bare minimum provided.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Deterministic AI safety policy engine with Z3 formal verification. Write, verify, simulate, and enforce machine-verifiable safety constraints for AI agents. Completely outside the LLM.
      11
      98 PyPI
      27
      Apache 2.0
    • A
      license
      A
      quality
      D
      maintenance
      A secure mathematical computation sandbox that enables LLMs to perform symbolic math operations like algebra, calculus, and equation solving via SymPy. It features low-latency execution through pre-warmed process pools and provides standardized JSON outputs for reliable agent integration.
      1
      2
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to execute arbitrary Python code securely in a sandboxed environment with resource limits and security constraints via MCP protocol.
      MIT