Give your agent finished lists from the live web: every row with its source, priced per match.
MCP Server: ai.specstream/specstream
This MCP server provides “finished lists” sourced from the live web. It returns results where each row includes its source information and pricing “per match,” as described in the server summary.
🛠️ Key Features
Produces finished lists from live web data
Returns results as rows
Includes a source for each row
Includes pricing per match
🚀 Use Cases
Generate curated, ready-to-use lists from current web content
Support workflows that need per-item provenance and match-based pricing
⚡ Developer Benefits
Structured row output with source attribution
Pricing included per match for downstream handling
⚠️ Limitations
The description only specifies “finished lists” with source and per-match pricing; no additional capabilities are stated.
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.
Python SDK, TypeScript SDK, OpenAI Agents SDK and LangChain
Connect an agent
The MCP server is https://api.specstream.ai/mcp (Streamable HTTP, 96 tools). Your agent works on your account: the same balance, permissions and spending limits you have.
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.
Put it in an environment variable, so no file holds it:
sh
export SPECSTREAM_API_KEY="ss_live_..."
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.
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.
Add to .vscode/mcp.json. VS Code asks for the key once and keeps it out of the file.
json
{"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}"}}}}
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.
import os
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
asyncwith 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.")
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.
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.
quote_capacity_work returns the price and the most the work can cost. A price lasts 30 minutes.
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.
get_find shows progress while rows arrive. list_find_rows returns results with the reason and the source for each fact.
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
sh
pip install specstream-client # Python 3.12+, import specstream_client, command: specstream
npm install @specstream/sdk # Node 22+
brew tap specstreamai/specstream-tools https://github.com/Specstreamai/specstream-tools
brew install specstream # the command line
python
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"])
ts
import { Client } from"@specstream/sdk";
const client = newClient({ apiKey: process.env.SPECSTREAM_API_KEY! });
const read = await client.compile("Datasets on urban tree canopy published since 2020 under an open license.");
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.
