specstream-toolsSAFE
Finished lists from the live web for your agent, every row with its source, priced before anything runs. MCP setup, plugins, skills, SDKs, n8n node and GitHub Action for SpecStream.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
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.
[](https://pypi.org/project/specstream-client/) [](https://www.npmjs.com/package/@specstream/sdk) [](https://www.npmjs.com/package/n8n-nodes-specstream) [](https://registry.modelcontextprotocol.io/v0.1/servers?search=ai.specstream) [](https://smithery.ai/servers/specstream/specstream)
This repository holds what you install around SpecStream: MCP client setup, agent plugins and skills, SDKs, the n8n node, a Gi
0fe159d2d9bbOBSERVED · 2026-10-12Install
Commands as the repository documents them. They are shown, not run.
claude mcp add --transport http specstream https://api.specstream.ai/mcp \
pip install specstream-mcp-stdio
pip install specstream-client # Python 3.12+, import specstream_client, command: specstream
npm install @specstream/sdk # Node 22+
pip install -r requirements.txt langchain-openai # or langchain-anthropic
pip install -r requirements.txt
Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned | |
| codex | mentioned | |
| cursor | mentioned | |
| gemini-cli | mentioned | |
| windsurf | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: approve-work description: Approve an exact price, up to the maximum the person set. This starts paid work. --- # Approve a price SpecStream is the live web data engine for teams and agents. Use the configured MCP server at `https://api.specstream.ai/mcp`. `authorize_capacity_work` starts paid work, so treat it as a write. It needs the reviewed `quote_id` and `quote_hash`, the approved maximum as an integer in `confirm_max_cents`, and a stable `idempotency_key`. A standing project or agent authority must cover this exact scope and limit. A funded account is not enough. Save the same key before you send the call. If the response is unclear, recover the same work with `get_capacity_request` or `get_capacity_quote`. Never create a new key, price or run just to recover a lost response. A price that expired or changed needs a new approval. Do not top up, subscribe, add a seat or open a payment page. If the balance or the authority is missing, say exactly what is missing and keep the request. Use `get_find` for progress. Rows appear while the run works, and a run can be stopped and keeps what it found. Only delivered matches are charged. Unsure results stay unsure.
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (6 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (11)
"NativeAuthStartData": { "handoff_id": string; "callback_url": string; "authorization_url": string; };.vscodeignore
import { requireConfirmMaxUsd } from "../../lib/confirm_max_usd.js";alias: { "@specstream/sdk": fileURLToPath(new URL("../../packages/sdk-ts/src/index.ts", import.meta.url)) },yield f"http://127.0.0.1:{server.server_port}", seen"download_url": f"http://127.0.0.1:{self.server.server_port}/export/one_use"client = Client("offline", base_url=f"http://127.0.0.1:{server.server_port}")langchain, langchain-mcp-adapters
openai-agents
@specstream/sdk, @types/node, typescript
release-it
Gates applied: no_behavioural_pass.
0fe159d2d9bbfull audit observations/trust-audit/skill/specstreamai__specstream-tools.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 0fe159d2d9bb | SAFE | B | 89 | first audit |
Questions
What does the specstream-tools skill do?
Finished lists from the live web for your agent, every row with its source, priced before anything runs. MCP setup, plugins, skills, SDKs, n8n node and GitHub Action for SpecStream.
Is specstream-tools safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can specstream-tools access on my machine?
The audit observed that it reaches the network and reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.
What do I need installed to use specstream-tools?
Its own instructions reference quote_hash and quote_id. Dependencies are not all pinned to exact versions, so what installs today may differ tomorrow.
Which assistants does specstream-tools work with?
Its documentation mentions claude-code, codex, cursor, gemini-cli and windsurf. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (0fe159d2d9bb), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.