
MetaGO Algorithms
MCP server exposing 927 deterministic algorithms as 57 tools, from coupling to PCA
- Pricing
- Open source
- Platforms
- macOS, Windows, Linux
- Runs
- Locally
- Version
- 1.0.2
- Listing updated
- 1 day ago
About MetaGO Algorithms
MetaGO Algorithms is an open-source MCP server for analytics and data. It runs locally on your machine and is started by your AI client.
This package turns MetaGO's algorithm library into callable MCP tools. It claims 927 algorithms across 14 trigger categories, organised in four layers: general entry, retrieval and discovery, 30 high-frequency specialised tools and 20 family tools. Categories include coupling calculation, multi-dimensional value assessment, distance metrics, correlation, dimensionality reduction such as PCA and SVD, security audit and frequency-domain processing.
The entry tools are execute and execute_sync, which run any algorithm by name, and get_statistics. Discovery tools list algorithms and families, search them semantically and return details for one, while specialised tools such as coupling_calculate, coupling_clustering, value_assess and build_value_vector handle the frequent jobs. Results are deterministic, so the same input gives the same output.
The vendor's own limits are public: 15 algorithms cannot be expressed under a JSON protocol, 6 lack sufficient fixtures, and bundled samples cover 906 of 927, with binding success not proving numeric correctness. It installs from npm, runs over stdio, and is a sibling of the MetaGO harness package.
Install
Run in a terminal
claude mcp add metago-algorithms -- npx -y @metago-ai/algorithmsAdd to claude_desktop_config.json
{
"mcpServers": {
"metago-algorithms": {
"command": "npx",
"args": [
"-y",
"@metago-ai/algorithms"
]
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"metago-algorithms": {
"command": "npx",
"args": [
"-y",
"@metago-ai/algorithms"
]
}
}
}Add to .vscode/mcp.json
{
"servers": {
"metago-algorithms": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@metago-ai/algorithms"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"metago-algorithms": {
"command": "npx",
"args": [
"-y",
"@metago-ai/algorithms"
]
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"metago-algorithms": {
"command": "npx",
"args": [
"-y",
"@metago-ai/algorithms"
]
}
}
}Tools this server provides (10)
Taken from the project documentation; the running server may differ.
- execute
- Execute any algorithm by name with parameters.
- execute_sync
- Synchronous algorithm execution.
- get_statistics
- Server statistics: tool count, algorithm count, layer distribution.
- list_algorithms
- List all algorithms with metadata.
- list_families
- List algorithm families.
- search_algorithms
- Semantic search over algorithm descriptions.
- get_algorithm_info
- Detailed information on a specific algorithm.
- coupling_calculate
- Coupling calculation tool.
- coupling_clustering
- Coupling clustering tool.
- value_assess
- Value assessment tool.
What it does
- Large algorithm catalogue
- 927 algorithms across 14 trigger categories.
- Run by name
- execute and execute_sync run any algorithm with parameters.
- Semantic discovery
- Search and list algorithms and families.
- Coupling and value tools
- Dedicated tools for coupling scores, clustering and value assessment.
- Statistical tools
- Distance, correlation and dimensionality reduction.
- Published limits
- The vendor lists algorithms it cannot cover or test fully.
Good for
- Let an agent compute a correlation or distance deterministically
- Reduce dimensions of a vector set with PCA or SVD
- Score relationship strength between items
- Find which algorithm fits a task via search
Pricing
Open source
npm package @metago-ai/algorithms; licence not detailed
Prices change. Check metago.life before you buy.
MetaGO Algorithms FAQ
How many tools does it expose?
57 tools backed by 927 algorithms.
Are the results deterministic?
The package describes the algorithms as deterministic.
What are the known gaps?
15 algorithms are unreachable under JSON and bundled samples cover 906 of 927.
How do I run it?
npx @metago-ai/algorithms over stdio.
Is MetaGO Algorithms free?
Yes. MetaGO Algorithms is open source, so you can use and self-host it for free.
How do I add MetaGO Algorithms to Claude Code?
Run this command in your terminal: claude mcp add metago-algorithms -- npx -y @metago-ai/algorithms
What are the best alternatives to MetaGO Algorithms?
The closest alternatives to MetaGO Algorithms are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to MetaGO Algorithms

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Agent-Native Analytics
MCP serverOpen-source analytics app where an AI agent builds charts and dashboards from your data
- Remote
- Open source
- 7.7K GitHub stars
- Analytics and data