python_mcp

python_local is an MCP server that exposes an interactive, persistent Python REPL to an agent. It provides a single tool (python_repl) to execute Python code in separate session states, and a resource mechanism to view per-session REPL history via a custom repl:// URI scheme.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ DevTools mcp python repl tools stdio local-execution
⚙ Agent Friendliness
48
/ 100
Can an agent use this?
🔒 Security
14
/ 100
Is it safe for agents?
⚡ Reliability
22
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
55
Documentation
45
Error Messages
0
Auth Simplicity
100
Rate Limits
0

🔒 Security

TLS Enforcement
0
Auth Strength
0
Scope Granularity
0
Dep. Hygiene
40
Secret Handling
40

No auth/authz is described (local stdio MCP server). Since it executes arbitrary Python code and captures stdout/stderr, it can exfiltrate secrets or perform harmful actions unless the host environment is trusted and appropriately sandboxed/isolated. TLS is not applicable to stdio-local MCP.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
30
Error Recovery
25
AF Security Reliability

Best When

You control the environment (local machine / trusted agent), want a lightweight tool for Python execution with session persistence, and can accept the security risks of running arbitrary Python.

Avoid When

You need strong authentication/authorization, remote/public exposure, or isolation against malicious code; you also want a stable externally managed API rather than a local MCP stdio server.

Use Cases

  • Agent-driven Python experimentation and prototyping in a persistent REPL session
  • Debugging or running small Python snippets with captured stdout/stderr
  • Inspecting prior REPL inputs/outputs for auditability within an agent workflow

Not For

  • Executing untrusted code from unknown users/agents without sandboxing
  • Production multi-tenant usage requiring strong isolation between users/sessions
  • High-volume, network-accessible execution services (it runs locally over stdio via MCP)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication mechanism is described; this appears intended for local/desktop usage via stdio MCP server process wiring.

Pricing

Free tier: No
Requires CC: No

No hosted service/pricing information is provided; it appears to be a self-hosted/local package.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Arbitrary Python execution can cause side effects in the persistent session state
  • Debugging MCP servers over stdio may be non-trivial without inspector tooling
  • No documented rate limiting or structured retry guidance is provided in the README

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for python_mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered