> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns. > > **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal): > ```bash > npx -y @scalekit-inc/cli setup -y > ``` > > Global: > ```bash > npm install -g @scalekit-inc/cli > scalekit setup -y > ``` > > Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`. > Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim. > [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/) --- # Connect AI agents to the Arcmira MCP server The Arcmira MCP connector routes your AI agent's tool calls to Arcmira's own MCP server through Scalekit. Each user signs in to Arcmira once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 4 tools. **Authentication:** OAuth 2.1/DCR **Categories:** Search, Productivity **Tools:** 4: 1 read, 2 write, 1 destructive **Users sign in with:** OAuth **OAuth app:** Scalekit's or your own **Built by:** Vendor MCP **Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=ARCMIRAMCP) ## Setup 1. ### Install the SDK **Node.js** ```bash npm install @scalekit-sdk/node dotenv ``` **Python** ```bash pip install scalekit-sdk-python python-dotenv ``` 2. ### Set your credentials Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**. ```sh title=".env" SCALEKIT_ENVIRONMENT_URL= SCALEKIT_CLIENT_ID= SCALEKIT_CLIENT_SECRET= ``` 3. ### Create the Arcmira MCP connection In **AgentKit > Connections**, create an Arcmira MCP connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/). Scalekit credentials are available for Arcmira MCP server, so you don't need to register an OAuth app. 4. ### Authorize a user and make your first call **Node.js** (`quickstart.mts`) ```typescript import { ScalekitClient } from '@scalekit-sdk/node' import 'dotenv/config' import { createInterface } from 'node:readline/promises' const scalekit = new ScalekitClient( process.env.SCALEKIT_ENVIRONMENT_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET, ) const actions = scalekit.actions const connector = 'arcmiramcp' const identifier = 'user_123' // Generate an authorization link for the user const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier }) console.log('Authorize Arcmira MCP:', link) const rl = createInterface({ input: process.stdin, output: process.stdout }) await rl.question('Press Enter after authorizing...') rl.close() // Make your first call const result = await actions.executeTool({ connector, identifier, toolName: 'arcmiramcp_arcmira_describe', toolInput: {}, }) console.log(result) ``` ```bash npx tsx quickstart.mts ``` **Python** (`quickstart.py`) ```python import os from scalekit import ScalekitClient from dotenv import load_dotenv load_dotenv() scalekit_client = ScalekitClient( env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"), client_id=os.getenv("SCALEKIT_CLIENT_ID"), client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"), ) actions = scalekit_client.actions connection_name = "arcmiramcp" identifier = "user_123" # Generate an authorization link for the user link_response = actions.get_authorization_link( connection_name=connection_name, identifier=identifier, ) print("Authorize Arcmira MCP:", link_response.link) input("Press Enter after authorizing...") # Make your first call result = actions.execute_tool( tool_input={}, tool_name="arcmiramcp_arcmira_describe", connection_name=connection_name, identifier=identifier, ) print(result) ``` ```bash python quickstart.py ``` Each user signs in once. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses. ## Tools Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool). **Node.js** ```typescript const result = await actions.executeTool({ toolName: 'arcmiramcp_arcmira_describe', toolInput: {}, connector: 'arcmiramcp', identifier: 'user_123', }) ``` **Python** ```python result = actions.execute_tool( tool_name="arcmiramcp_arcmira_describe", tool_input={}, connection_name="arcmiramcp", identifier="user_123", ) ``` `result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call. ### `arcmiramcp_arcmira_describe` The arcmira client reference · Read-only Returns the reference for the typed arcmira client the execute tools run: method arguments, return fields, entity ID rules, examples, errors, the budget and monitor rules, and documentation links. The optional topic narrows it to a method or subject. Reads no indexed content and bills nothing. Docs: https://arcmira.com/docs/mcp-server Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `intent` (`string`, optional): Optional: the user's request in a few words. Logged with this call to improve Arcmira. - `topic` (`string`, optional): One word to narrow the reference, like sponsors, resolve, transcript, monitors or dates. Omit for the whole reference (about 25,000 characters). Example input: `{}` ### `arcmiramcp_arcmira_execute_read` Research with a program · Write Runs JavaScript against the Arcmira API through the arcmira client: indexed YouTube and podcast transcripts, mentions, sponsors, recommendations, coverage, Premium transcripts (a Premium read of an untranscribed video starts a transcription that uses credits from the account's plan, then its on-demand budget, and reports its charge), and the user's monitors. Input is an async function body with arcmira, ArcmiraError, and console in scope. Output is bounded JSON with the result first, then the call count, rate limit, build and capped logs. Methods and examples: arcmira_describe. Filters require entity, channel, or video IDs. Limits: 30 seconds, 40 API calls, and 12,000 characters of output in total, 3,000 per string, and 100 items per array. Read only: no. Destructive: no. Idempotent (safe to retry): no. Inputs: - `code` (`string`, required): JavaScript source, the body of async function (arcmira, ArcmiraError, console) { ... }. Return a value or console.log lines. No import or export. - `intent` (`string`, optional): Optional: the user's request in a few words. Logged with this call to improve Arcmira. Example input: `{"code":""}` ### `arcmiramcp_arcmira_feedback` Tell Arcmira what went wrong · Write Saves a feedback record for the Arcmira team. Send one when a result was wrong, slow, empty or confusing, or when the user wants a source or capability Arcmira lacks. Put what they were doing and any source links in note. Each call adds a record; repeated calls create separate records. Costs nothing. Read only: no. Destructive: no. Idempotent (safe to retry): no. Inputs: - `category` (`string`, required): wrong_entity: the wrong person, company or show. bad_data: a wrong count, date, quote or label. missing: something that should be there is not. slow: it took too long. confusing: a result, error or rule was hard to act on. other. One of: `wrong_entity`, `bad_data`, `missing`, `slow`, `confusing`, `other`. - `note` (`string`, required): What happened in a sentence or two: what the user was doing, what came back, what they expected, and any source links. No credentials or personal details. - `call_id` (`string`, optional): The call_id a result named (mcpc_ followed by 32 hex characters), for the call this is about. - `intent` (`string`, optional): Optional: the user's request in a few words. Logged with this call to improve Arcmira. - `request_id` (`string`, optional): The request_id of the error this is about, when there was one. Example input: `{"category":"wrong_entity","note":""}` ### `arcmiramcp_arcmira_execute_write` Change Arcmira monitors · Destructive Runs JavaScript like arcmira_execute_read, plus the monitor writes: create, update (including paused), addEntities, addName and attachTrackers. Nothing is deleted. The MONITORS section of arcmira_describe has the fields and results. Limits: 30 seconds, 40 API calls, and 12,000 characters of output in total, 3,000 per string, and 100 items per array. Read only: no. Destructive: yes. Idempotent (safe to retry): no. Inputs: - `code` (`string`, required): JavaScript source, the body of async function (arcmira, ArcmiraError, console) { ... }. Return a value or console.log lines. No import or export. - `intent` (`string`, optional): Optional: the user's request in a few words. Logged with this call to improve Arcmira. Example input: `{"code":""}` ## Related Other Search connectors ([all 55](/agentkit/connectors/?category=search)): - [Supadata](/agentkit/connectors/supadata/): Scalekit connector, API key, 21 tools - [Exa](/agentkit/connectors/exa/): Scalekit connector, API key, 21 tools - [Brave Search](/agentkit/connectors/brave/): Scalekit connector, API key, 18 tools --- ## More Scalekit documentation | Resource | What it contains | When to use it | |----------|-----------------|----------------| | [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content | | [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas | | [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |