FutureAGI MCP server for AI agents and assistants

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with FutureAGI MCP or direct API to run evaluations, inspect observability traces, manage datasets, and review annotations through natural language.

FutureAGI logoFutureAGI
Api Key

FutureAGI is an AI evaluation and observability platform for testing, tracing, simulating, and improving AI systems. Use it to measure model quality, debug failures, manage datasets, and close the loop with annotation workflows.

9 Tools

Try FutureAGI now

Type what you want done — sign in and watch it run live in the Tool Router playground.

TOOL ROUTER PLAYGROUND
FutureAGI
Try asking
TOOLS

Supported Tools

Every FutureAGI action and event your agent gets out of the box.

List Agent Definitions

List one page of agent definitions in the connected FutureAGI organization, optionally filtering by type, name, assistant ID, or agent ID.

List Annotation Labels

List one page of FutureAGI annotation labels by type, name, project, or dataset, optionally including usage counts.

List Annotation Queues

List one page of FutureAGI annotation queues by status or name, optionally including item counts.

List Custom Eval Configs

List custom evaluation configurations, optionally restricted to a FutureAGI project or evaluation task.

List Datasets

List one page of datasets in the connected FutureAGI organization, optionally searching by name.

List Eval Tasks

List one page of FutureAGI evaluation tasks, optionally filtering by project ID or task name.

List Personas

List one page of built-in and workspace personas for FutureAGI simulations, with type, simulation-mode, and text filters.

List Run Tests

List one page of configured FutureAGI run tests without executing them, optionally filtering by name, source type, or prompt template.

List Scenarios

List one page of FutureAGI simulation scenarios, optionally filtering by agent definition, agent type, or search text.

SETUP GUIDE

Connect FutureAGI MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
Install the Composio SDK and your agent framework
2

Create a session with MCP enabled

typescript
import { Composio } from "@composio/core";

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["futureagi"],
  mcp: true,
});
Create a session scoped to FutureAGI and read its MCP URL and headers
3

Connect your agent to the MCP server

typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";

const client = await createMCPClient({
  transport: { type: "http", url: mcp.url, headers: mcp.headers },
});

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  tools: await client.tools(),
  prompt: "List recent FutureAGI evaluation runs and summarize the failing test cases",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
Pass the session's MCP URL and headers to your agent and run a FutureAGI request
SETUP GUIDE

Connect FutureAGI API Tool with your Agent

1

Install Composio

typescript
npm install @composio/core @composio/openai openai
Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
2

Create a Composio session

typescript
import OpenAI from "openai";
import { Composio } from "@composio/core";
import { OpenAIResponsesProvider } from "@composio/openai";

const composio = new Composio({ provider: new OpenAIResponsesProvider() });
const client = new OpenAI();

const session = await composio.create("your-user-id", { toolkits: ["futureagi"] });
const tools = await session.tools();
Initialize Composio with the OpenAI Responses provider and create a session scoped to FutureAGI
3

Run FutureAGI tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "List recent FutureAGI evaluation runs and summarize the failing test cases" }],
});

while (response.output.some((o) => o.type === "function_call")) {
  const outputs = await composio.provider.handleToolCalls(session, response.output);
  response = await client.responses.create({
    model: "gpt-5.6-sol",
    tools,
    previous_response_id: response.id,
    input: outputs,
  });
}

console.log(response.output_text);
Send a request, execute the FutureAGI tool calls through the session, and print the final answer

Why Use Composio?

AI Native FutureAGI Integration

  • Supports both FutureAGI MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable evaluation, observability, dataset, simulation, and annotation workflows
  • Rich coverage for reading, writing, and querying FutureAGI data without custom integration code

Managed Auth

  • Securely store and use your FutureAGI API key without hard-coding it in agent code
  • Central place to manage, scope, and revoke FutureAGI access across users and environments
  • Per user and per environment credentials, so local testing and production stay cleanly separated

Agent Optimized Design

  • FutureAGI tools are exposed with clear schemas that AI agents can understand and call reliably
  • Tools are tuned using real error and success patterns to improve reliability over time
  • Comprehensive execution logs, so you can see which evaluation, trace, dataset, or annotation action ran and why

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access FutureAGI
  • Scoped, least privilege access to FutureAGI evaluation, observability, dataset, and annotation resources
  • Full audit trail of agent actions to support debugging, review, and compliance
FAQ

Frequently asked questions

Yes, FutureAGI requires you to configure your own API key credentials. Once set up, Composio handles secure credential storage and API request handling for you.

Yes! Composio's Tool Router enables agents to use multiple toolkits. Learn more.

Yes. Composio is SOC 2 Type II compliant and is built to keep your FutureAGI connection and credentials secure. OAuth tokens and API keys are encrypted, and sensitive customer data is protected at rest and in transit.

Composio also undergoes independent security testing and continuously monitors its systems for security threats. You can review the latest reports and policies in the Composio Trust Center.

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

Create the key in your FutureAGI account settings, then paste it once on Composio's connection page. Composio stores it encrypted and uses it only for the FutureAGI actions your agent runs. Nobody else in your workspace can read it, and you can revoke it inside FutureAGI at any time.

When you connect a FutureAGI account through Composio, every action runs under that account, so anything the agent creates, sends, or changes shows up in FutureAGI as done by you. Keep an approval step in your prompt for actions with side effects, such as sending or deleting, and have the agent draft first.

Whatever the credentials you connect allow inside FutureAGI. If FutureAGI lets you scope a key to specific permissions, create a scoped one so the agent can only do what you intend. You can revoke the key inside FutureAGI at any time.

Yes. Composio supports multiple connected accounts for the same app, and that works in Claude, ChatGPT, or any other assistant you connect through Composio. Give each FutureAGI connection a name such as work or personal, and the assistant uses the one you mention in the request. Each account keeps its own credentials and nothing is merged.

The connection stops working the moment FutureAGI rejects the old key. Create a new key in FutureAGI and reconnect the account from the Composio dashboard or by asking your agent to reconnect FutureAGI. Nothing else changes.

Composio's free Hobby plan includes 100,000 tool calls per month with no credit card, which covers most personal FutureAGI use. Paid plans add higher limits and team features. Your FutureAGI plan and its API limits still apply as usual.

Built-in connectors usually give one AI access to a limited set of apps. Many people use Composio because it lets their AI connect to more apps than it normally supports, or connect to multiple accounts for the same app (e.g. connect Claude to multiple FutureAGI accounts).

With Composio, you connect FutureAGI once and then use it across different AI assistants without setting it up separately in each one. Connect your apps to Composio once, then connect Composio to whichever AI you use, whether that's Claude, ChatGPT, Hermes, or your own custom assistant.

Start with FutureAGI.It takes 30 seconds.

Managed auth, hosted MCP servers, and every FutureAGI tool your agent needs.Free to start.

Start building