methods-mcp runs on your own machine — the client starts it, so there is no endpoint to ping. 180 installs a week from pypi. Last commit 16 Apr 2026.
MCP server for structured methods extraction + reproducibility heuristics on academic papers.
Today is the operative word: we check methods-mcp every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add methods-mcp -- uvx methods-mcp
{
"mcpServers": {
"methods-mcp": {
"args": [
"methods-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.methods-mcp]
command = "uvx"
args = ["methods-mcp"]
{
"mcpServers": {
"methods-mcp": {
"args": [
"methods-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"methods-mcp": {
"args": [
"methods-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
ANTHROPIC_API_KEY (Required for LLM-driven extraction tools (extract_methods, summarize_paper, methods_repro_review).), GITHUB_TOKEN (Optional. Raises the GitHub REST API rate limit used by reproducibility assessment.), METHODS_MCP_MODEL (Override the default Claude model (default: claude-sonnet-4-6).).
The author declared them in the registry entry; get the values from the project itself.
The only MCP server for Arabic academic research — search, read & cite Arabic + English papers.
MCP server for academic papers, citations, authors, ECOS dossiers, and Federal Register text.
TerraDeed MCP server — x402 web scraping & structured extraction. Pay-per-call with USDC on Base.
Browser MCP server: budgeted page reads, honest unread accounting, structured extraction.
Browser MCP server: budgeted page reads, honest unread accounting, structured extraction.
Academic research MCP server for paper search, citation checks, graphs, and deep research.
Paper-backed quant trading methods and a deterministic, no-LLM decision helper for serious traders.
Structured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer.
Answers built from our own checks of this server.