Skip to main content
Glama
Eis4TY

SymPy Sandbox MCP

by Eis4TY
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SYMMCP_LOG_LEVELNolog levelINFO
SYMMCP_POOL_SIZENoworker pool size10
SYMMCP_HINT_LEVELNohint level (none/short/medium)medium
SYMMCP_QUEUE_WAIT_SECNoqueue wait timeout (sec)2
SYMMCP_MEMORY_LIMIT_MBNomemory cap per worker (MB)150
SYMMCP_EXEC_TIMEOUT_SECNoper execution timeout (sec)3
SYMMCP_MAX_OUTPUT_CHARSNooutput truncation threshold1200

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
sympyA

SymPy sandbox tool: execute Python/SymPy math code.

Safety boundaries:

  • Only sympy/math imports and calls are allowed.

  • System calls, file I/O, network access, and dynamic execution are blocked.

Input rules:

  • Single argument: code (str).

  • You must print() the final answer; otherwise out may be empty.

  • Use multiple print() lines for multiple outputs.

Recommended workflow:

  1. Define symbols and assumptions.

  2. Derive/solve step by step.

  3. Simplify intermediate expressions (simplify/factor/expand).

  4. Print final results.

Retry guidance:

  • E_AST_BLOCK: remove unsafe statements and keep pure math code only.

  • E_TIMEOUT: reduce problem size, split steps, simplify before solving.

  • E_MEMORY: reduce dimensions or avoid constructing huge objects at once.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.5/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'sympy' has a clear and distinct purpose: executing Python/SymPy math code within a sandboxed environment.

Naming Consistency5/5

Since there is only one tool, naming consistency is inherently perfect. The tool name 'sympy' is straightforward and matches the server's purpose, with no other tools to compare against for patterns.

Tool Count2/5

A single tool is too few for the apparent scope of a SymPy sandbox, which could benefit from more granular operations like simplify, solve, or differentiate. This minimal set may force agents to bundle multiple steps into one call, reducing flexibility and increasing error risk.

Completeness2/5

The tool surface is severely incomplete for mathematical computation. While the single tool can execute arbitrary SymPy code, it lacks dedicated tools for common operations (e.g., simplification, solving equations, calculus), making it harder for agents to reliably perform structured tasks without manual coding in each call.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources