mcpField
A
Agent Stack Directory

Agent Stack Directory

Remote
agentstackdirectory.comDeveloper Tools0Updated 1w ago

About Agent Stack Directory

Agent Stack Directory is a searchable dataset of infrastructure products for AI agents, for developers and coding agents evaluating tools. Its MCP server supports searching, inspecting, and comparing listings using current directory data.

Key features

  1. 01Search listings by query and filters
  2. 02Inspect product details and alternatives
  3. 03Compare two to four products
  4. 04Browse categories and counts
  5. 05Read JSON and CSV dataset snapshots

Use cases

  1. 01Find open-source agent sandboxes
  2. 02Compare infrastructure products
  3. 03Check alternatives in a product category

MCP support

The read-only MCP server exposes search_tools, get_tool, compare, and list_categories to MCP clients. It is available through a stateless Streamable HTTP endpoint or a local stdio setup.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://agentstackdirectory.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Agent Stack Directory: MCP server and open dataset

An open dataset of infrastructure tools for AI agents (cloud browsers, sandboxes, memory, search APIs, email, integrations, payments, voice, observability, frameworks and auth) plus a small MCP server so AI coding tools can query it while you build.

Tools

ToolInputReturns
search_toolsquery?, category?, open_source?, limit? (1 to 50, default 10)Matching tools ranked by keyword match
get_tooltool (slug or name)Summary, official site, open-source flag, last link check, alternatives in the same category
comparetools (2 to 4 slugs or names)Side-by-side table, notable differences, head-to-head page URL when one exists
list_categoriesnoneEvery category with key, description and tool counts

Every tool is read-only. Results come back as readable text plus structuredContent JSON.

Example prompts:

  • "Which sandboxes for running agent code are open source?"
  • "Compare E2B and Daytona."
  • "What are the alternatives to Browserbase?"

Listed in the official MCP Registry as com.agentstackdirectory/agent-stack-directory. Server card: https://agentstackdirectory.com/.well-known/mcp/server-card.json

Install (remote, nothing to run locally)

Claude Code
claude mcp add --transport http agent-stack-directory https://agentstackdirectory.com/mcp
Cursor

.cursor/mcp.json in your project, or ~/.cursor/mcp.json for all projects:

{
  "mcpServers": {
    "agent-stack-directory": {
      "url": "https://agentstackdirectory.com/mcp"
    }
  }
}
VS Code

.vscode/mcp.json in your workspace:

{
  "servers": {
    "agent-stack-directory": {
      "type": "http",
      "url": "https://agentstackdirectory.com/mcp"
    }
  }
}

Or from a terminal:

code --add-mcp '{"name":"agent-stack-directory","type":"http","url":"https://agentstackdirectory.com/mcp"}'

Install (local, stdio)

Needs Node 18 or newer. npx builds the server from this repository on first run.

Claude Code
claude mcp add agent-stack-directory -- npx -y github:gmansystems/agent-stack-directory
Cursor
{
  "mcpServers": {
    "agent-stack-directory": {
      "command": "npx",
      "args": ["-y", "github:gmansystems/agent-stack-directory"]
    }
  }
}
VS Code
{
  "servers": {
    "agent-stack-directory": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "github:gmansystems/agent-stack-directory"]
    }
  }
}
From a clone
git clone https://github.com/gmansystems/agent-stack-directory
cd agent-stack-directory
npm install
node dist/stdio.js

Environment variables (optional):

VariableDefaultPurpose
AGENT_STACK_DATA_URLhttps://agentstackdirectory.com/data.jsonWhere to fetch the dataset
AGENT_STACK_DATA_FILEunsetRead a local JSON file instead, for offline use, e.g. data/agent-stack-directory.json

The stdio server caches the dataset in memory for 10 minutes and keeps serving the last good copy if a refresh fails.

Dataset

data/agent-stack-directory.json holds categories and listings. Each listing has:

FieldMeaning
slugStable identifier, used in directory URLs
nameProduct name
urlOfficial site
categoryCategory key (see categories)
summaryOne plain sentence on what it does, written from the vendor's own site
taglineThe vendor's own tagline
open_sourcetrue when the product is marked open source
addedDate added to the directory
verifiedDate the official link was last checked

CSV copies: data/agent-stack-directory.csv and data/categories.csv. Refresh the snapshot with npm run snapshot.

Sponsorship never changes the data or the search ranking. The dataset has no sponsored fields.

Development

npm install
npm test                 # unit tests plus MCP client tests over stdio and Streamable HTTP
npm run test:remote      # live check of https://agentstackdirectory.com/mcp with the MCP client
npm run build:worker     # bundle src/worker.ts for the Cloudflare Pages Function

Layout:

  • src/core.ts: data loading and the tool logic, no I/O
  • src/server.ts: MCP server definition (official TypeScript SDK)
  • src/stdio.ts: stdio entry point (agent-stack-directory-mcp bin)
  • src/worker.ts: stateless Streamable HTTP handler for Cloudflare Workers or Pages Functions

To host your own remote copy on Cloudflare, bundle src/worker.ts and call handleMcpRequest(request, loader) from a Worker.

License

Corrections and new tools: https://agentstackdirectory.com/submit/ or open an issue.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.