repl-mcp

Run persistent stateful Python sessions with timeouts, isolation, and tool bridging.

Source

third_party_registry

Updated

2026-07-12

// securityCaution

Runs locally
Open source

Running security audit…

Credentials
Network egress
Code execution
Data access
Supply chain

// install

Copy the install command and let the AI configure it · recommended for beginners

No copy-paste install info for "repl-mcp" yet — see the docs or source repo.

// examples

Iterative Python debugging

Prompt

Run this script in the persistent Python REPL and keep variable state. If it errors, identify the cause, fix it step by step, and return the working version with key changes explained:

import pandas as pd

df = pd.read_csv('sales.csv')
print(df.groupby('region')['revenue'].sum().sort_valeus())

Expected

Returns error analysis, corrected code, and execution results from the same session state.

Run data computation with timeout control

Prompt

Run the following analysis task in the Python REPL with a reasonable timeout. If it times out or crashes, stop safely, explain why, and suggest optimizations: load a 1-million-row CSV, calculate monthly active users, and output the first 12 months of trends.

Expected

Returns execution status, result summary, or a timeout/crash explanation with performance suggestions.

Bridge other tools from code

Prompt

In the persistent Python session, write a script that first calls other MCP tools in the project to fetch data, then cleans, aggregates, and outputs a final table in Python. Keep intermediate variables for follow-up analysis.

Expected

Returns an executable script, tool-calling workflow details, and a result table with preserved session state.