Paws-onSAFE
A comprehensive Model Context Protocol (MCP) server implementing the latest specification.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A comprehensive Model Context Protocol (MCP) server implementing the latest MCP 2025-03-26 specification. Demonstrates MCP capabilities including tools, resources, prompts, roots, and enhanced sampling with model preferences. Features HackerNews and GitHub API integrations with AI-powered analysis through advanced MCP sampling.
🎯 Current Status
✅ Production-Ready Core Features (3/5 test suites passing)
- MCP Tools (9/9) - All tools working perfectly including enhanced sampling
- MCP Resources (15/15) - All resources working perfectly
- MCP Prompts (14/14) - All prompt templates working perfectly
- MCP Protocol Compliance - Full MCP 2025-03-26 specification support
- Enhanced Sampling - Model preferences and context-aware sampling working
⚠️ Known Limitations
- MCP Roots - Framework concurrency limitations (functionality works, test infrastructure issues)
- Enhanced Sampling Tests - Server concurrency constraints under load testing
The core MCP functionality is fully operational and production-ready.
📁 Project Structure
paws-on-mcp/ ├── src/ # Source code │ ├── mcp_server.py # Main MCP server (MCP 2025-03-26) │ └── mcp_cli_client.py # CLI client for testing ├── tests/ # Comprehensive test suite │ ├── run_tests.py # Complete test runner │ ├── test_mcp_tools.py # Tools functionality tests │ ├── test_mcp_resources.py # Resources tests │ ├── test_mcp_prompts.py # Prompts tests │ ├── test_mcp_roots.py # Roots tests (MCP 2025-03-26) │ └── test_enhanced_sampling.py # Enhanced sampling tests ├── docs/ # Documentation │ ├── architecture.md # Technical architecture │ ├── blog.md # Development insights │ └── CLI_README.md # CLI usage guide ├── requirements.txt # Python dependencies └── README.md # This
e1c5eb347f14OBSERVED · 2026-10-03Exposed tools (6)
5 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
analyze_hackernews_trends_with_ai | read | Analyze HackerNews trends using AI through sampling. |
code_review_with_ai | read | Get AI-powered code review insights for a GitHub repository. |
create_sampling_request | write | Create a sampling request according to MCP 2025-03-26 specification. |
get_github_repo_info | read | Get detailed information about a specific GitHub repository. |
get_server_prompts | read | List all available prompt templates. |
search_hackernews | read | Search HackerNews stories by title. |
Trust audit
SAFEgrade B · trust 87/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (8)
streamable-http
The server will start on `http://127.0.0.1:8000/mcp/` with the following startup message:
🚀 Starting Unified MCP Server on http://127.0.0.1:8000/mcp/
If no server URL is specified, it defaults to `http://127.0.0.1:8000/mcp/`.
python run_tests.py --server http://127.0.0.1:3000 info
print("🚀 Starting Unified MCP Server on http://127.0.0.1:8000/mcp/")mcp, pillow, httpx, requests, rich
Gates applied: no_behavioural_pass, no_license.
e1c5eb347f14full audit observations/trust-audit/mcp-server/hemanth__paws-on.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-03 | e1c5eb347f14 | SAFE | B | 87 | first audit |
Questions
What is the Paws-on MCP server?
A comprehensive Model Context Protocol (MCP) server implementing the latest specification.
What tools does Paws-on expose?
6 in total: 5 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Paws-on safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (87/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Paws-on need?
No credential environment variables were found in its source, so it appears to need none.
How does Paws-on run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (e1c5eb347f14), read on 2026-10-03. The repository is watched and re-audited when it changes.