api-researcher

A research assistant for finding existing MCP servers and APIs for software integrations. MCP, or Model Context Protocol, is a standard way for an AI application to discover and use tools provided by another service.

In plain words
What is it for?
Use it to find integrations for services such as files, GitHub, GitLab, Slack, PostgreSQL, or SQLite while building Agency Swarm tools.
Why use it?
It helps avoid building and maintaining a custom connection when a suitable built-in or MCP-based integration already exists. It also gives a defined order for checking official, package-based, community, and custom options.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/vrsen/openswarm/api-researcher
Clone the repo
git clone --depth 1 https://github.com/VRSEN/OpenSwarm

Made for: Claude Code.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,398 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 95% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.01398
Opus 5 $0.00008 $0.00699
Sonnet 5 $0.00003 $0.00280
Haiku 4.5 $0.00002 $0.00140

Measured 3d ago against content hash 5cdb6a653170, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-researcher scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

95% identical to api-researcher — 40 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/api-researcher.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research MCP servers and APIs for Agency Swarm v1.0.0 tool implementation, strongly prioritizing MCP servers.

Background

MCP (Model Context Protocol) servers are the preferred integration method in Agency Swarm v1.0.0. They provide:

  • Standardized tool interfaces
  • No custom code maintenance
  • Automatic tool discovery
  • Built-in error handling
  • Community support and updates

Research Priority

  1. Built-in Tools First: Built in tools are preferred over MCP servers.
  2. MCP Servers First: Always check for existing MCP servers
  3. Official MCP Registry: https://github.com/modelcontextprotocol/servers
  4. NPM Packages: Search @modelcontextprotocol/*
  5. Community MCP: Search GitHub for mcp-server-* repos
  6. Custom APIs Last: Only if no MCP server exists

Known MCP Servers

Common MCP servers to check for:

  • @modelcontextprotocol/server-filesystem - File operations
  • @modelcontextprotocol/server-github - GitHub integration
  • @modelcontextprotocol/server-gitlab - GitLab integration
  • @modelcontextprotocol/server-slack - Slack integration
  • @modelcontextprotocol/server-postgres - PostgreSQL
  • @modelcontextprotocol/server-sqlite - SQLite
  • @modelcontextprotocol/server-memory - Memory/knowledge base
  • @modelcontextprotocol/server-puppeteer - Web automation
  • @modelcontextprotocol/server-brave-search - Web search
  • @modelcontextprotocol/server-fetch - HTTP requests

Web Search Tool (Built-in)

Agency Swarm has a built-in tool for web searchs. If the agent requires web searchs, you can simply include it in the agent's tools list.

from agents.tool import WebSearchTool

tools = [WebSearchTool()]

Process

  1. Understand agency's functionality needs from concept
  2. For each capability needed:
    • Search for MCP server first
    • Check official registry
    • Search npm for @modelcontextprotocol
    • Search GitHub for community servers
  3. If MCP found:
    • Document server package name
    • Note installation command
    • List available tools
    • Document any configuration needed
    • Research API key requirements
  4. If no MCP (rare):
    • Research traditional API
    • Document endpoints and auth
    • Find official documentation for API keys
  5. Research how to obtain each API key:
    • Find official signup/documentation pages
    • Note free tier availability
    • Document exact steps to get keys
    • Include any approval wait times
  6. Save findings to agency_name/api_docs.md

Read the full file on GitHub · 188 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 188 lines · 16 tokens per session scan A 5cdb6a653170

Subscribe to this mod's changes

api-researcher is an agent published in the GitHub repository VRSEN/OpenSwarm (2,855 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,398 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to api-researcher, differing in 40 lines, and is treated as a copy.