1. Conduid
  2. Developer Tools
  3. ta-lib-mcp-server
MCP server · Developer Tools

ta-lib-mcp-server

A Model Context Protocol server providing tools to access to TA-Lib technical analysis indicators.

Unclaimed last commit 7 months ago devtools
37Low

Scored 16 days ago · breakdown

About ta-lib-mcp-server

ta-lib-mcp-server is an MCP server published by yalcin in the Developer Tools category: a Model Context Protocol server providing tools to access to TA-Lib technical analysis indicators.

Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

uvx
uvx ta-lib-mcp-server
pip
pip install ta-lib-mcp-server

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about ta-lib-mcp-server

Powered by Claude · Grounded in docs

I know everything about ta-lib-mcp-server. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ✓README presentThe repository ships documentation.

5 checks have not been run yet.

README

ta-lib-mcp

Read-only Python MCP server for TA-Lib indicator discovery and computation.

What It Exposes

  • talib_list_indicators: list available indicators with group, category, and search filters.
  • talib_get_indicator_info: inspect one indicator's inputs, outputs, parameters, and category.
  • talib_compute_indicator: compute an indicator from numeric OHLCV-like arrays.
  • talib_list_categories: list indicator categories (Trend, Momentum, Volume, etc.) with descriptions.
  • talib_get_version_info: report MCP, Python, and TA-Lib versions.

Requirements

  • Python 3.13+
  • mcp[cli]
  • Optional: TA-Lib (pip install "ta-lib-mcp-server[talib]")

If TA-Lib is missing, the server still starts and returns actionable errors for TA-Lib tools.

Install

pip install -e ".[dev,talib]"

Run

ta-lib-mcp

MCP Client Configuration

Claude Desktop

{
  "mcpServers": {
    "ta-lib": {
      "command": "ta-lib-mcp",
      "env": {
        "TALIB_MCP_LOG_LEVEL": "INFO"
      }
    }
  }
}

Codex

[mcp_servers.talib]
command = "ta-lib-mcp"
args = []

[mcp_servers.talib.env]
TALIB_MCP_LOG_LEVEL = "INFO"

Gemini CLI

{
  "mcpServers": {
    "ta-lib": {
      "command": "ta-lib-mcp",
      "env": {
        "TALIB_MCP_LOG_LEVEL": "INFO"
      }
    }
  }
}

Development

pip install -e ".[dev,talib]"
pytest
ruff check src tests
ruff format src tests
mypy src

Engineering Rules

  • Read-only server behavior only; no stateful or exchange-connected operations.
  • External MCP tool inputs are validated in src/ta_lib_mcp/validators.py.
  • Do not use eval or exec.

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About ta-lib-mcp-server

How do I install ta-lib-mcp-server?

Run uvx ta-lib-mcp-server, then add the server to your MCP client's configuration.

Is ta-lib-mcp-server safe to use with an AI agent?

Its trust score is 37 out of 100 (low). It passes 1 of the 1 static security checks run so far. It has no ConduID identity yet, so agent calls to it are not receipted.

Is ta-lib-mcp-server still maintained?

The last commit was 7 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.