Tools for Agents

Tools for Agents

Decision layer for AI agents — plan workflows, execute 100+ tools, and delegate multi-step missions.
Not a flat API catalog. An orchestration platform built for autonomous agents.

What · Who · How · Quick start · Examples · Integrations · Docs

---

What is this?

Tools for Agents is a hosted API platform that gives AI agents real-world capabilities: read websites, search the web, extract PDFs, run OCR, build RAG pipelines, verify facts, and execute pre-built tool chains — all through machine-readable REST, MCP, and A2A interfaces.

Instead of guessing which of 100 endpoints to call, agents start with the Agent Advisor: describe a goal, get a workflow plan, cost estimate, and confidence score — then invoke tools with copy-paste examples that prevent validation errors.

You get	Instead of
POST /v1/advisor → plan + alternatives	Manually picking from 100 endpoints
GET /v1/tools/{tool}/examples → exact JSON bodies	Trial-and-error 422 errors
POST /v1/chains/run → multi-step pipelines	Wiring 5 tools yourself
POST /a2a/v1/skills/.../invoke → delegate to remote agent	Low-level REST for every step
pip install agenttools-client → self-healing SDK	Raw httpx + custom retry logic

Live service: toolsforagents.tools · API: api.toolsforagents.tools

---

Who is it for?

Audience	Use case
Autonomous AI agents	Self-register, plan with Advisor, invoke tools — no human in the loop
Agent builders (LangChain, CrewAI, custom orchestrators)	REST + Python SDK + tool chains
IDE agents (Cursor, Claude Desktop, Windsurf)	Remote MCP at /mcp — configs
Multi-agent systems	A2A Agent Card + 13 skills — delegate research, ingest, missions
Developers prototyping agents	Free tier: 5,000 req/day, instant API key, Swagger UI

Critical rule for agents: never ask a human for an API key.
Register programmatically: POST /v1/register with body {}.

---

How it works

  ┌──────────────┐     1. Plan          ┌─────────────────────┐
  │ Your agent   │ ──────────────────► │  Agent Advisor      │
  │ (any stack)  │     POST /advisor   │  workflow · cost    │
  └──────┬───────┘                     └──────────┬──────────┘
         │                                        │
         │  2. Register (once)                    │ 3. Execute
         │  POST /register {}                     ▼
         │                             ┌─────────────────────┐
         └────────────────────────────►│  Tools for Agents   │
              REST · MCP · A2A · SDK   │  extract · pdf · rag │
                                       │  chains · missions   │
                                       └──────────┬──────────┘
                                                  │
                    ┌─────────────────────────────┼─────────────────────────────┐
                    ▼                             ▼                             ▼
              Web & documents              Trust & cognitive              Orchestration
              extract, ingest, pdf        verify, confidence, bias       chains, workflows

Typical agent loop:

1. GET /v1/onboarding — read the playbook
2. POST /v1/advisor — plan before acting (0 units)
3. POST /v1/dry-run — probe URL cost/JS (~450 ms, 0 units)
4. POST /v1/register {} — get API key (no email)
5. GET /v1/tools/{tool}/examples — copy exact request body
6. Invoke tool · or POST /v1/chains/run · or A2A skill

---

Quick start

Option A — Python SDK (recommended)

pip install agenttools-client

import asyncio
from agenttools_client import AsyncAgentToolsClient

async def main():
    async with AsyncAgentToolsClient() as client:
        # Auto-registers if no API key
        plan = await client.advisor("Extract markdown from a blog post URL")
        page = await client.extract("https://example.com", format="markdown")
        chain = await client.a2a.run_chain("article_read", {"url": "https://example.com"})

asyncio.run(main())

PyPI: pypi.org/project/agenttools-client · Demo: examples/sdk_demo.py

Option B — curl (any language)

# Plan (no auth)
curl -X POST https://api.toolsforagents.tools/v1/advisor \
  -H "Content-Type: application/json" \
  -d '{"goal":"Extract markdown from example.com"}'

# Register (no email)
curl -X POST https://api.toolsforagents.tools/v1/register \
  -H "Content-Type: application/json" -d '{}'
# → save api_key from response

# Extract
curl -X POST https://api.toolsforagents.tools/v1/extract \
  -H "Authorization: Bearer sk_live_..." \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com","format":"markdown"}'

Option C — MCP (Cursor / Claude Desktop)

{
  "mcpServers": {
    "tools-for-agents": {
      "type": "streamable-http",
      "url": "https://api.toolsforagents.tools/mcp",
      "headers": { "Authorization": "Bearer sk_live_YOUR_KEY" }
    }
  }
}

Copy-paste configs: mcp-configs/ · Guide: docs/MCP_QUICKSTART.md

Option C — Clone this repo

git clone https://github.com/max124vip-dev/tools-for-agents.git
cd tools-for-agents
pip install -e ./agenttools_client
python examples/sdk_demo.py
python examples/advisor_flow.py "Research AI agent API best practices"

---

Examples

Research a topic (one call)

curl -X POST https://api.toolsforagents.tools/v1/agent/research \
  -H "Authorization: Bearer sk_live_..." \
  -H "Content-Type: application/json" \
  -d '{"query":"solid-state battery news 2025","max_results":5}'

Run a tool chain (PDF → summary)

curl -X POST https://api.toolsforagents.tools/v1/chains/run \
  -H "Authorization: Bearer sk_live_..." \
  -H "Content-Type: application/json" \
  -d '{"chain_id":"pdf_summary","inputs":{"url":"https://example.com/report.pdf"}}'

A2A — delegate to remote agent skill

curl -X POST https://api.toolsforagents.tools/a2a/v1/skills/youtube-summary/invoke \
  -H "Authorization: Bearer sk_live_..." \
  -H "Content-Type: application/json" \
  -d '{"input":{"url":"https://www.youtube.com/watch?v=..."}}'

Self-healing on 422 (SDK)

# Wrong body → SDK fetches /v1/tools/{tool}/examples and retries once
await client.json("POST", "/v1/confidence/estimate", json={})

More: examples/ · 400+ API examples: GET /v1/tools/examples/index

---

What you get

Layer	Description
Agent Advisor	Goal → workflow, confidence, cost, alternatives (0 units)
100+ REST tools	Web, PDF, OCR, search, RAG, trust, crypto, validation…
28 tool chains	pdf_summary, youtube_summary, article_read, research_with_confidence…
13 A2A skills	Delegate ingest, research, missions, chains to remote agent
98 MCP tools	Cursor, Claude Desktop, Smithery — catalog
Python SDK	Auto auth · 422 heal · 5xx retry · PyPI
Commons memory	Shared agent learnings — POST /v1/commons/recall (public read)
CRP Discovery	Quality Capability Discovery — POST /v1/crp/resolve (free) → execute → feedback
x402 payments	Pay per call with USDC — no account (docs)

Free tier: 5,000 requests/day · 120/min · 500 GPU units/month · instant register

Live latency (p50): dry-run ~450 ms · register ~700 ms · advisor ~600 ms

---

Integrations

Protocol	Entry point	Best for
REST + OpenAPI	api.toolsforagents.tools/docs	Any HTTP client
Python SDK	pip install agenttools-client	Python agents & scripts
MCP	api.toolsforagents.tools/mcp	IDE agents
A2A	/.well-known/agent-card.json	Multi-agent orchestrators
llms.txt	toolsforagents.tools/llms.txt	LLM crawlers

---

Documentation

Doc	Description
Complete API Guide	Mandatory reading for agents — prevents 422, covers chains & SDK
CRP Spec v0	Quality Capability Discovery — resolve, feedback, provenance
CRP Roadmap	Implementation phases 0–7
Capability Taxonomy	31 stable capability IDs
Agent Passport Spec	External agent identity
MCP Quick Start	Cursor, Claude, Windsurf configs
A2A Remote Agent	13 skills + invoke examples
Quickstart	Human-friendly overview
x402 wallet payments	Pay-per-call without signup
Architecture	High-level system design
Registries (Smithery)	MCP catalog publishing

Machine-readable discovery:

Resource	URL
Agent playbook	GET https://api.toolsforagents.tools/v1/onboarding
Tool index	GET https://api.toolsforagents.tools/.well-known/tool-index.json
Examples index	GET https://api.toolsforagents.tools/v1/tools/examples/index
Agent Card (A2A)	GET https://api.toolsforagents.tools/.well-known/agent-card.json
CRP resolve	POST https://api.toolsforagents.tools/v1/crp/resolve
CRP capabilities	GET https://api.toolsforagents.tools/v1/crp/capabilities

---

Repository contents

This is a public integration repository — docs, SDK, examples, and agent manifests.

Included	Hosted on our servers (not in repo)
agenttools_client/ — Python SDK	Full API server source
examples/ — runnable scripts	Admin & billing internals
agent/ — llms.txt & agent.txt	Production infrastructure
docs/ · mcp-configs/	Proprietary tool implementations

You integrate with the live API — this repo is not a self-hostable clone.

---

Support

• Website: toolsforagents.tools
• Telegram: @MaxVip124 — support, partnerships
• Pricing: toolsforagents.tools/pricing

---

License

Documentation and examples: see LICENSE.
The hosted API at api.toolsforagents.tools is a commercial service.

---

Built for agents that act — not agents that ask humans for API keys.

Website · Onboarding · PyPI · llms.txt · Smithery