specstream-tools

The live web data engine for teams and agents.

Website  ·  Docs  ·  Pricing  ·  MCP Registry

Finished lists from the live web for your agent, every row with its source, priced before anything runs. Ask for the list you need in plain words and get all of it: only the matches, each with the page it came from, kept current and sent where you work. You pay only for the matches.

Your agent asks for "food banks in Texas, with their annual revenue" and gets rows it can cite, each with the page behind it. It sees the price first, and a search that finds nothing costs nothing.

This repository holds what you install around SpecStream: MCP client setup, agent plugins and skills, SDKs, the n8n node, a GitHub Action, and examples. The product itself runs at specstream.ai. Licensed MIT.

Connect an agent

The MCP server is https://api.specstream.ai/mcp (Streamable HTTP, 97 tools). Your agent works on your account: the same balance, permissions and spending limits you have.

1. Open Agents & API in the workspace and create an API key. Give it only what the task needs: read, prepare, or execute, the projects it may use, an expiry, and a spending limit.

2. Put it in an environment variable, so no file holds it:

   export SPECSTREAM_API_KEY="ss_live_..."
   

3. Add the server to your client, below.

Clients that support MCP sign-in can connect without a key. Each guide at specstream.ai/docs/mcp shows the current steps.

New accounts start with $10 of work free for 30 days, no card.

Claude

In Claude, go to Customize > Connectors, choose Add custom connector, name it SpecStream and paste https://api.specstream.ai/mcp. Steps for both sign-in and a key: docs/mcp/claude.

Claude Code

claude mcp add --transport http specstream https://api.specstream.ai/mcp \
  --header "Authorization: Bearer $SPECSTREAM_API_KEY"

Or install the plugin, which adds the server and the four skills. It signs you in through your browser the first time, so no key is needed:

/plugin marketplace add specstream/specstream-tools
/plugin install specstream@specstream

ChatGPT

Go to ChatGPT Plugins, choose the plus button, then Add custom MCP server. Paste https://api.specstream.ai/mcp under Connection and set Authentication to OAuth. Steps: docs/mcp/chatgpt.

Codex

Add to ~/.codex/config.toml:

[mcp_servers.specstream]
url = "https://api.specstream.ai/mcp"
bearer_token_env_var = "SPECSTREAM_API_KEY"

Cursor

Add to ~/.cursor/mcp.json, or .cursor/mcp.json in one project:

{
  "mcpServers": {
    "specstream": {
      "url": "https://api.specstream.ai/mcp",
      "headers": { "Authorization": "Bearer ${env:SPECSTREAM_API_KEY}" }
    }
  }
}

VS Code

Add to .vscode/mcp.json. VS Code asks for the key once and keeps it out of the file.

{
  "inputs": [
    { "type": "promptString", "id": "specstream-key", "description": "SpecStream API key", "password": true }
  ],
  "servers": {
    "specstream": {
      "type": "http",
      "url": "https://api.specstream.ai/mcp",
      "headers": { "Authorization": "Bearer ${input:specstream-key}" }
    }
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "specstream": {
      "serverUrl": "https://api.specstream.ai/mcp",
      "headers": { "Authorization": "Bearer ${env:SPECSTREAM_API_KEY}" }
    }
  }
}

Zed, Cline, and Continue

Cline also connects to the hosted server directly with OAuth sign-in: cline mcp install specstream --transport http https://api.specstream.ai/mcp. Zed and Continue, and Cline if you prefer a key, use the stdio proxy. It forwards your key from the environment and nothing else.

pip install specstream-mcp-stdio

Zed, in settings.json:

{
  "context_servers": {
    "specstream": {
      "command": "specstream-mcp-stdio",
      "args": [],
      "env": { "SPECSTREAM_MCP_URL": "https://api.specstream.ai/mcp" }
    }
  }
}

Cline, in cline_mcp_settings.json:

{
  "mcpServers": {
    "specstream": {
      "command": "specstream-mcp-stdio",
      "args": [],
      "env": { "SPECSTREAM_MCP_URL": "https://api.specstream.ai/mcp" }
    }
  }
}

Continue, in .continue/mcpServers/specstream.yaml:

name: SpecStream
version: 1.0.0
schema: v1
mcpServers:
  - name: specstream
    type: stdio
    command: specstream-mcp-stdio
    args: []
    env:
      SPECSTREAM_MCP_URL: https://api.specstream.ai/mcp
      SPECSTREAM_API_KEY: ${{ secrets.SPECSTREAM_API_KEY }}

Start Zed and Cline from a shell where SPECSTREAM_API_KEY is set. Agents installing SpecStream for someone can follow llms-install.md.

Gemini CLI

Install the extension (the MCP server plus instructions to show the price and wait for a yes):

gemini extensions install https://github.com/specstream/specstream-tools

Or add only the server:

gemini mcp add --transport http specstream https://api.specstream.ai/mcp \
  --header "Authorization: Bearer $SPECSTREAM_API_KEY"

Or in ~/.gemini/settings.json:

{
  "mcpServers": {
    "specstream": {
      "httpUrl": "https://api.specstream.ai/mcp",
      "headers": { "Authorization": "Bearer $SPECSTREAM_API_KEY" }
    }
  }
}

OpenCode

Add the plugin to opencode.json. It adds the SpecStream server and the four skills, and opencode mcp auth specstream signs you in through your browser:

{
  "$schema": "https://opencode.ai/config.json",
  "plugin": ["opencode-specstream"]
}

Details and options: integrations/opencode.

Replit

The button adds SpecStream to Replit Agent; you sign in when the Project Editor asks. No key goes in the link.

Any other client that takes a URL

Lovable, Gumloop, Relevance AI, Lindy, Manus, Genspark and the rest: add a remote MCP server, paste https://api.specstream.ai/mcp, and sign in when asked. If the client only takes headers, use Authorization: Bearer $SPECSTREAM_API_KEY.

Agents that speak A2A

SpecStream is also an A2A agent. The Agent Card is at https://api.specstream.ai/.well-known/agent-card.json (A2A 1.0, with the 0.3 fields) and the JSON-RPC endpoint is https://api.specstream.ai/a2a. Without a key, it reads the request back and prices it:

curl -s https://api.specstream.ai/a2a -H 'Content-Type: application/json' -H 'A2A-Version: 1.0' \
  -d '{"jsonrpc":"2.0","id":1,"method":"SendMessage","params":{"message":{"messageId":"m1","role":"ROLE_USER","parts":[{"text":"Plumbers in Denver with a phone number"}]}}}'

With Authorization: Bearer $SPECSTREAM_API_KEY (or an OAuth token), the reply is a task waiting for approval. Reply on the task with a data part {"confirm_max_cents": N}, where N is the quoted maximum, to run it; GetTask returns the rows, each value with its source_url.

n8n

Install the community node from Settings > Community nodes: n8n-nodes-specstream. It reads a request, shows the quote, approves the maximum you type in, and returns the results. Three importable workflows are in integrations/n8n/workflows. An AI agent in n8n can also use the MCP Client Tool node with endpoint https://api.specstream.ai/mcp, transport HTTP Streamable and a Bearer credential.

LangChain

pip install -U langchain-specstream

from langchain.agents import create_agent
from langchain_specstream import specstream_tools

agent = create_agent("anthropic:claude-sonnet-5-5", tools=specstream_tools(max_price_usd=5))

Two tools and a retriever. The agent writes the request and picks how many rows; the price cap stays in your code, where the model can't raise it. Every row comes back with the page it was read from. Details in packages/langchain-specstream.

To load every SpecStream tool over MCP instead:

import os
from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
    "specstream": {
        "transport": "streamable_http",
        "url": "https://api.specstream.ai/mcp",
        "headers": {"Authorization": f"Bearer {os.environ['SPECSTREAM_API_KEY']}"},
    }
})
tools = await client.get_tools()

A full agent is in examples/langchain-mcp.

LlamaIndex

pip install -U llama-index-tools-specstream

from llama_index.core.agent.workflow import FunctionAgent
from llama_index.tools.specstream import SpecStreamToolSpec

agent = FunctionAgent(tools=SpecStreamToolSpec(max_price_usd=5).to_tool_list(), llm=llm)

The same two tools as a tool spec, plus a retriever that returns one node per row with its source in the metadata. The price cap stays on the spec, out of the model's reach. Details in packages/llama-index-tools-specstream.

CrewAI

pip install -U crewai-specstream

from crewai import Agent
from crewai_specstream import specstream_tools

analyst = Agent(role="Funding analyst", goal="Answer with a source for every claim",
                backstory="You work from lists, not from memory.", tools=specstream_tools(max_price_usd=5))

The same two tools as CrewAI tools, with the key kept as a secret and async crews left unblocked. Details in packages/crewai-specstream.

Vercel AI SDK

npm install @specstream/ai-sdk ai zod

import { generateText, stepCountIs } from "ai";
import { specstreamTools } from "@specstream/ai-sdk";

const { text } = await generateText({
  model: "openai/gpt-5-mini",
  tools: specstreamTools({ maxPriceUsd: 5 }),
  stopWhen: stepCountIs(5),
  prompt: "Find dental clinics in Lisbon with online booking, with their website.",
});

Works with AI SDK 6 and 7. Details in packages/ai-sdk.

OpenAI Agents SDK

import os
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async with MCPServerStreamableHttp(
    name="SpecStream",
    params={
        "url": "https://api.specstream.ai/mcp",
        "headers": {"Authorization": f"Bearer {os.environ['SPECSTREAM_API_KEY']}"},
    },
    cache_tools_list=True,
) as server:
    agent = Agent(name="Researcher", instructions="Use SpecStream for lists.", mcp_servers=[server])
    result = await Runner.run(agent, "Food banks in Texas, with their annual revenue. Show me the price first.")

A full agent is in examples/openai-agents-sdk.

Any other client that speaks remote MCP over Streamable HTTP works with the address above and an Authorization: Bearer header.

What the agent does, in order

Nothing is spent until a person – or an agent inside a limit a person set – approves a price.

1. compile reads the request and returns how SpecStream understood it: the kind of thing, the conditions every result must meet, the facts to bring back.
2. quote_capacity_work returns the price and the most the work can cost. A price lasts 30 minutes.
3. authorize_capacity_work approves that exact quote, with the maximum in cents (confirm_max_cents) and a stable idempotency_key, so a retry never pays twice.
4. get_find shows progress while rows arrive. list_find_rows returns results with the reason and the source for each fact.
5. export_find, share_find, and send_to_destination move results on. Reading, exporting, and sharing cost nothing.

Each delivered result costs 10 cents, 30 cents or $1 depending on how many facts it carries. A search that finds nothing is free. See pricing.

The four skills in skills/ teach an agent this order and where to stop and ask: compile, review-work, approve-work, continue-work.

SDKs and command line

pip install specstream-client        # Python 3.12+, import specstream_client, command: specstream
npm install @specstream/sdk          # Node 22+
brew tap specstream/specstream-tools https://github.com/specstream/specstream-tools
brew install specstream              # the command line

import os
from specstream_client import Client

client = Client(os.environ["SPECSTREAM_API_KEY"])
read = client.compile("Datasets on urban tree canopy published since 2020 under an open license.")
offer = client.quote_capacity_work({
    "ast_hash": read["ast_hash"], "operation": "find",
    "requested_units": read["ast"]["limit"]["max"],
})
print(offer["maximum_cents"], offer["expires_at"])

import { Client } from "@specstream/sdk";

const client = new Client({ apiKey: process.env.SPECSTREAM_API_KEY! });
const read = await client.compile("Datasets on urban tree canopy published since 2020 under an open license.");

Working scripts that run a request end to end are in examples/python-sdk and examples/typescript-sdk.

GitHub Action

- uses: specstream/specstream-tools/actions/find-action@v1
  with:
    request: Open tenders on SAM.gov for translation services with a deadline after November 1. Include the buyer and the estimated value.
    api_key: ${{ secrets.SPECSTREAM_API_KEY }}
    confirm_max_usd: "10"

The step stops if the price is above confirm_max_usd.

Three requests

Say what you need the way you would to a colleague. These come from the request templates in the product.

Software companies in Germany with 50 to 500 employees that are hiring salespeople. Include the job post and contact email.One row per company, with its size, the sales job post and the contact email the company published. Each row says in one line why it fits, with the page each fact came from. Companies SpecStream could not confirm are listed apart, and they cost nothing.

Open tenders on SAM.gov for translation services with a deadline after November 1. Include the buyer and the estimated value.One row per notice, with the buyer, the estimated value, the deadline and a link to the notice. Code compares the deadline with the date you gave.

Rust command-line tools on GitHub with more than 1,000 stars, pushed to in the last month, under an MIT or Apache license.One row per repository, with its stars, last push and license. Code compares the stars and the date with your numbers, and each row links to the repository.

Reading goes where those things live: registries and official APIs, maps and directories, job boards, research indexes, news, and each result's own site. SpecStream reads at the moment you ask.

Docs and support

• Getting started, API, SDKs, MCP
• Pricing
• Agent guide and llms.txt
• Support: [email protected]
• Security reports: see SECURITY.md

License

MIT. See LICENSE. SpecStream the service is governed by its terms.