SpecStream MCP connector for AI agents

Tools your research agent reaches for on SpecStream MCP, scoped per user.

CALL ANY TOOL

OAuth 2.1 list research: 61 SpecStream MCP tools to compile requests, run finds, enrich collections, and reconcile sources.

specstreammcp_compile

Understand a request

Read a request for a list, written in everyday words in any language: companies and local businesses, products and stores, jobs, papers, clinical trials, grants, tenders, datasets, repositories and packages, apps, books or podcasts. Return how SpecStream understood it: what to find, the conditions every result must meet, the facts to bring back (required or optional), how many, and in what order, with the ast_hash that identifies this reading. To add facts to, extend or refresh a list you have, name it with its parent_find_id and the operation: what it finds and its conditions stay as they are, and only the new facts to bring back or the new count are read. The caller must be allowed to read that list. Nothing runs and nothing is charged.

Parameters

Name

Type

Required

Description

string

Required

The request for a list, written in everyday words in any language. SpecStream reads it and returns how it understood it; nothing runs and nothing is charged.

locale

string

Optional

The locale code for the request, written as a two-letter language code, a hyphen and a two-letter region code. It defaults to en-US. Default: `en-US`.

retained

string

Optional

Optional reference to a list you already have, to extend it, add facts to it or refresh it. It names the earlier run and the operation, and what that list finds and its conditions stay as they are.

specstreammcp_edit_spec

Change what to find or bring back

specstreammcp_get_capacity_balance

Check the balance

specstreammcp_get_capacity_quote

Reopen a quote

specstreammcp_get_capacity_request

Find work already started

specstreammcp_get_collection

Open a collection

specstreammcp_get_find

Check on a run

specstreammcp_get_input_research

Review imported research

specstreammcp_get_project

Open a project

specstreammcp_get_reconciled_input

Read where filled cells came from

specstreammcp_get_reconciliation

Read a comparison

specstreammcp_get_reconciliation_fields

List fields to match on

specstreammcp_get_spec

Open a saved request

specstreammcp_get_spec_revision

Open one version

specstreammcp_get_web_source

Read a website source

specstreammcp_get_web_source_preview

Read a source preview

specstreammcp_list_activity

Lists

specstreammcp_list_collections

List collections

specstreammcp_list_find_rows

Read the results

specstreammcp_list_projects

List projects

specstreammcp_list_reconciliations

List recent comparisons

specstreammcp_list_request_templates

Start from an example

specstreammcp_list_specs

List saved requests

specstreammcp_list_web_sources

List website sources

specstreammcp_list_your_fields

Read your fields

specstreammcp_open_list_file

List file

specstreammcp_open_specstream

Lists

specstreammcp_open_specstream_panel

Selected list

specstreammcp_preview_web_source

Read a website source again

specstreammcp_read_specstream_record_notes

Read record notes

specstreammcp_read_specstream_settings

List settings

specstreammcp_replay_find_decisions

Replay the checks

specstreammcp_search_lists

Find a list or record to mention

specstreammcp_search_workspace

Search your work

specstreammcp_show_specstream_lists

Your lists

specstreammcp_show_specstream_records

Results

specstreammcp_add_specstream_record_note

Add a record note

specstreammcp_apply_reconciliation

Fill a list from chosen pairs

specstreammcp_export_find

Download the results

specstreammcp_import_csv

Import a CSV or Excel file

specstreammcp_prepare_reconciliation

Compare two lists

specstreammcp_quote_imported_list

Price filling in an imported list

specstreammcp_quote_more_facts

Price more facts

specstreammcp_quote_more_results

Price more results

specstreammcp_quote_new_list

Price a new list

specstreammcp_quote_refresh

Price a refresh

specstreammcp_resolve_specstream_record_note

Resolve a record note

specstreammcp_save_web_source_list

Save a source preview as a list

specstreammcp_set_your_field

Mark records

specstreammcp_teach_web_source

Teach a website source

specstreammcp_update_specstream_settings

Save list settings

specstreammcp_cancel_find

Stop a run

specstreammcp_delete_specstream_record_note

Remove a record note

specstreammcp_edit_specstream_record_note

Edit your record note

specstreammcp_revoke_share

Stop sharing results

specstreammcp_run_imported_list

Fill in an imported list

specstreammcp_run_more_facts

Add facts to a list

specstreammcp_run_more_results

Get more results

specstreammcp_run_new_list

Run a new list

specstreammcp_run_refresh

Refresh a list

specstreammcp_share_find

Share results

Build your Agent

Same OAuth 2.1 vault and scoped tool list across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
const sk = new ScalekitClient(
  process.env.SCALEKIT_ENVIRONMENT_URL,
  process.env.SCALEKIT_CLIENT_ID,
  process.env.SCALEKIT_CLIENT_SECRET,
);
const page = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["specstreammcp"], toolNames: [
    "specstreammcp_compile",
    "specstreammcp_edit_spec",
    "specstreammcp_get_capacity_balance",
  ]}, pageSize: 100,
});

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";
const sk = new ScalekitClient(
  process.env.SCALEKIT_ENVIRONMENT_URL,
  process.env.SCALEKIT_CLIENT_ID,
  process.env.SCALEKIT_CLIENT_SECRET,
);
const page = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["specstreammcp"], toolNames: [
    "specstreammcp_compile",
    "specstreammcp_edit_spec",
    "specstreammcp_get_capacity_balance",
  ]}, pageSize: 100,
});
const openai = new OpenAI();

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";
const sk = new ScalekitClient(
  process.env.SCALEKIT_ENVIRONMENT_URL,
  process.env.SCALEKIT_CLIENT_ID,
  process.env.SCALEKIT_CLIENT_SECRET,
);
const page = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["specstreammcp"], toolNames: [
    "specstreammcp_compile",
    "specstreammcp_edit_spec",
    "specstreammcp_get_capacity_balance",
  ]}, pageSize: 100,
});
const anthropic = new Anthropic();

import { ScalekitClient } from "@scalekit-sdk/node";
const sk = new ScalekitClient(
  process.env.SCALEKIT_ENVIRONMENT_URL,
  process.env.SCALEKIT_CLIENT_ID,
  process.env.SCALEKIT_CLIENT_SECRET,
);
const page = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["specstreammcp"], toolNames: [
    "specstreammcp_compile",
    "specstreammcp_edit_spec",
    "specstreammcp_get_capacity_balance",
  ]}, pageSize: 100,
});

Try these prompts

Copy a prompt into your agent. Each one maps to SpecStream list research for the signed-in user.

Understand a request

Copy the prompt

Copied

Compile this request without running it: Series B fintech companies in India that hire ML engineers.

Copy the prompt

Copied

Read my natural-language list request and return the conditions and facts SpecStream will bring back.

Copy the prompt

Copied

Edit the last compile so company size is at least 50 employees without rewording the whole request.

Run and enrich lists

Copy the prompt

Copied

Run the find for EU climate-tech Series A startups and show the first 10 rows with sources.

Copy the prompt

Copied

Open collection for my last find and list which cells still need enrichment.

Copy the prompt

Copied

Import research from this spreadsheet URL into my current SpecStream project.

Reconcile and share

Copy the prompt

Copied

Reconcile my imported CRM list against the live web find and show field mismatches.

Copy the prompt

Copied

Check capacity balance before I start a 500-row enrichment run.

Copy the prompt

Copied

Share the finished find with my teammate as a read-only link.

SEE HOW AUTH WORKS

Your users connect once. Their SpecStream OAuth 2.1 tokens stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

SpecStream MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

SpecStream MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

SpecStream MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

SpecStream MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Reuse the same per-user OAuth 2.1 vault and audit chain on other Search connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared SpecStream key makes every compile and find look like a bot. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_acct

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

SpecStream MCP today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access SpecStream MCP as the user or a shared key?

Per-user resolution. Each tool call uses the signed-in user's SpecStream OAuth 2.1 token, so list research attributes to that user in the audit log.

Where is the SpecStream token stored?

In Scalekit's AES-256 vault, namespaced per tenant. Tokens refresh automatically. You revoke access from one dashboard without rotating a shared secret across every agent.

Can I limit what the agent does in SpecStream MCP?

Yes. Filter tool names in listScopedTools (for example specstreammcp_compile only) and Scalekit checks that scope before the API call.

What happens when a user revokes access?

The next SpecStream tool call fails closed for that user. Other users and other connectors are unaffected. The revoke is logged.

Does SpecStream MCP include write and destructive tools?

Yes. Docs list 61 tools: 36 read, 15 write, and 10 destructive. Scope tool names tightly so agents only get the actions you intend.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit