Tools for Agents MCP server
Commit Sep 3, 2026Provides an orchestration platform for AI agents to plan workflows, execute over 100 tools, and delegate multi-step missions via REST, MCP, and SDKs.
Also known as max124vip-dev/tools-for-agents, tools-for-agents
- Stars
- 2
- Tools
- β
- Downloads, 30 days
- β
- Latest version
- 0.1.0
- Last commit
- Sep 3, 2026
- License
- β
What is Tools for Agents MCP?
Tools for Agents provides an orchestration platform for AI agents to plan workflows, execute over 100 tools, and delegate multi-step missions via REST, MCP, and SDKs.
Summary generated from the project's README
About Tools for Agents MCP server
Tools for Agents serves as a decision layer and orchestration platform designed specifically for autonomous AI agents. It provides a hosted environment where agents can plan complex workflows, execute over 100 specialized tools, and manage multi-step missions. Instead of manually selecting individual endpoints, agents use the Agent Advisor to receive workflow plans, cost estimates, and confidence scores before taking action.
Developers can integrate this platform using a Python SDK, REST APIs, or the Model Context Protocol (MCP) for IDE agents like Claude Desktop and Cursor. The system supports multi-agent coordination through A2A skills and pre-built tool chains for tasks like PDF summarization or web extraction. A free tier is available with a limit of 5,000 requests per day, and the platform allows for programmatic registration to ensure agents can operate without human intervention.
What you can do with it
- 1Plan complex agent workflowsAn agent can describe a high-level goal to receive a structured plan and cost estimate before execution.
Written from the project's README. Every use case is checked against a quote from it.
How to install Tools for Agents MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Tools for Agents MCP in Claude Code
$ claude mcp add --transport http tools-for-agents https://api.toolsforagents.tools/mcpInstall Tools for Agents MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"tools-for-agents": {
"url": "https://api.toolsforagents.tools/mcp"
}
}
}Install Tools for Agents MCP in VS Code
.vscode/mcp.json
{
"servers": {
"tools-for-agents": {
"type": "http",
"url": "https://api.toolsforagents.tools/mcp"
}
}
}Install Tools for Agents MCP in VS Code CLI
$ code --add-mcp '{"name":"tools-for-agents","type":"http","url":"https://api.toolsforagents.tools/mcp"}'Install Tools for Agents MCP in Codex
$ codex mcp add tools-for-agents --url https://api.toolsforagents.tools/mcpInstall Tools for Agents MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.tools-for-agents] url = "https://api.toolsforagents.tools/mcp"
Install Tools for Agents MCP in Gemini CLI
$ gemini mcp add -s user --transport http tools-for-agents https://api.toolsforagents.tools/mcpInstall Tools for Agents MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"tools-for-agents": {
"url": "https://api.toolsforagents.tools/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 2026Full report βNot verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work Β· What to fix for more points
- Source repository linked and reachablemax124vip-dev/tools-for-agents is public and reachablegithub.com/max124vip-dev/tools-for-agents βPass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-09-03github.com/max124vip-dev/tools-for-agents βPass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeEndpoint did not answer initialize: HTTP 530Finding
README
View on GitHubWhat 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 β 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 β then invoke tools with copy-paste examples that prevent validation errors.
| You get | Instead of |
|---|---|
POST /v1/advisor β plan + alternatives |
Manually picking from 100 endpoints |
GET /v1/tools/{tool}/examples β exact JSON bodies |
Trial-and-error 422 errors |
POST /v1/chains/run β multi-step pipelines |
Wiring 5 tools yourself |
POST /a2a/v1/skills/.../invoke β delegate to remote agent |
Low-level REST for every step |
pip install agenttools-client β self-healing SDK |
Raw httpx + custom retry logic |
Live service: toolsforagents.tools Β· API: api.toolsforagents.tools
Who is it for?
| Audience | Use case |
|---|---|
| Autonomous AI agents | Self-register, plan with Advisor, invoke tools β 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 β configs |
| Multi-agent systems | A2A Agent Card + 13 skills β 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/registerwith body{}.
How it works
ββββββββββββββββ 1. Plan βββββββββββββββββββββββ
β Your agent β βββββββββββββββββββΊ β Agent Advisor β
β (any stack) β POST /advisor β workflow Β· cost β
ββββββββ¬ββββββββ ββββββββββββ¬βββββββββββ
β β
β 2. Register (once) β 3. Execute
β POST /register {} βΌ
β βββββββββββββββββββββββ
ββββββββββββββββββββββββββββββΊβ Tools for Agents β
REST Β· MCP Β· A2A Β· SDK β extract Β· pdf Β· rag β
β chains Β· missions β
ββββββββββββ¬βββββββββββ
β
βββββββββββββββββββββββββββββββΌββββββββββββββββββββββββββββββ
βΌ βΌ βΌ
Web & documents Trust & cognitive Orchestration
extract, ingest, pdf verify, confidence, bias chains, workflows
Typical agent loop:
GET /v1/onboardingβ read the playbookPOST /v1/advisorβ plan before acting (0 units)POST /v1/dry-runβ probe URL cost/JS (~450 ms, 0 units)POST /v1/register {}β get API key (no email)GET /v1/tools/{tool}/examplesβ copy exact request body- Invoke tool Β· or
POST /v1/chains/runΒ· or A2A skill
Quick start
Option A β 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 Β· Demo: examples/sdk_demo.py
Option B β 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 '{}'
# β 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 β 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/ Β· Guide: docs/MCP_QUICKSTART.md
Option C β 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 β 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 β 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 β SDK fetches /v1/tools/{tool}/examples and retries once
await client.json("POST", "/v1/confidence/estimate", json={})
More: examples/ Β· 400+ API examples: GET /v1/tools/examples/index
What you get
| Layer | Description |
|---|---|
| Agent Advisor | Goal β 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 β catalog |
| Python SDK | Auto auth Β· 422 heal Β· 5xx retry Β· PyPI |
| Commons memory | Shared agent learnings β POST /v1/commons/recall (public read) |
| CRP Discovery | Quality Capability Discovery β POST /v1/crp/resolve (free) β execute β feedback |
| x402 payments | Pay per call with USDC β no account (docs) |
Free tier: 5,000 requests/day Β· 120/min Β· 500 GPU units/month Β· instant register
Live latency (p50): dry-run ~450 ms Β· register ~700 ms Β· 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 β prevents 422, covers chains & SDK |
| CRP Spec v0 | Quality Capability Discovery β resolve, feedback, provenance |
| CRP Roadmap | Implementation phases 0β7 |
| 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 β docs, SDK, examples, and agent manifests.
| Included | Hosted on our servers (not in repo) |
|---|---|
| agenttools_client/ β Python SDK | Full API server source |
| examples/ β runnable scripts | Admin & billing internals |
| agent/ β llms.txt & agent.txt | Production infrastructure |
| docs/ Β· mcp-configs/ | Proprietary tool implementations |
You integrate with the live API β this repo is not a self-hostable clone.
Support
- Website: toolsforagents.tools
- Telegram: @MaxVip124 β support, partnerships
- Pricing: toolsforagents.tools/pricing
License
Documentation and examples: see LICENSE.
The hosted API at api.toolsforagents.tools is a commercial service.
Tools for Agents MCP questions
How do I add Tools for Agents MCP to Claude Code?
Run claude mcp add --transport http tools-for-agents https://api.toolsforagents.tools/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Tools for Agents MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How can an agent register for the service?
Agents can register programmatically without an email by using the POST /v1/register endpoint with an empty body.
What is the Agent Advisor used for?
The Agent Advisor allows agents to describe a goal and receive a workflow plan, cost estimate, and confidence score before execution.
Can I use this with Cursor or Claude Desktop?
Yes, you can integrate it with IDE agents like Cursor or Claude Desktop using the remote MCP interface.