Skip to main content
Glama
codeprimate

Math MCP Server

by codeprimate

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_HOSTNoHost to bind the HTTP server (only used with streamable-http transport)0.0.0.0
MCP_PATHNoHTTP endpoint path (only used with streamable-http transport)/mcp
MCP_PORTNoPort for the HTTP server (only used with streamable-http transport)8008
MCP_TRANSPORTNoTransport mode: stdio (default) or streamable-httpstdio
MCP_OUTPUT_DIRNoBase directory for plot output files/outputs/
MCP_OUTPUT_VOLUMENoOutput volume mount path (bind mount or named volume)./outputs

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": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
math_batchA

Run multiple tools in one request. Pass a list of objects with 'name' (tool name) and optional 'arguments' (dict). Results are returned in the same order. At most 64 calls per request. Execution is parallel with concurrency limited by CPU count minus one.

math_lsA

List available math tools. Call with no args to get categories and a flat list of all tools (name, intent). Then: use math_man(name) for one tool's parameters, or math_ls(category) for full descriptors (name, description, inputSchema) for every tool in that category. Finally call math(name, arguments) to run.

math_manA

Return the full descriptor (name, description, inputSchema) for a named math tool. Use after math_ls() to get parameters for a chosen tool, then call math(name, arguments) to run.

mathA

Execute a math tool by name. Discovery: call math_ls() first to get tool names and intents; get parameters via math_man(name) or math_ls(category); then call math(name, arguments) with the chosen tool name and its arguments.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.1/5.0

Scored across 4 tools

Disambiguation4/5

math_ls and math_man both provide tool descriptors and could be confused when seeking detailed parameter info, but their descriptions clearly separate listing from individual manual lookup. math and math_batch are distinct as single vs. batch execution.

Naming Consistency3/5

math_ls and math_man follow a Unix-style abbreviation convention while math_batch is descriptive, and math drops the prefix entirely. The shared math_ prefix helps, but the mix of styles is noticeable.

Tool Count4/5

Four tools is a reasonable size for a meta-server that delegates to a dynamic math tool set. It feels slightly thin because no actual math operations are exposed statically, but the scaffolding tools each earn their place.

Completeness5/5

The set covers the full discovery, documentation, execution, and batching lifecycle with no obvious dead ends. Agents can go from listing tools to inspecting parameters to running single or batched operations. Assuming the underlying math tool registry is populated, this is complete.

Maintenance

ActivityMaintained
ResponsivenessNo issues