archestra

Map of the Archestra documentation: every page's slug, title, description, and section headings. Call this first to orient yourself, then read_doc for full pages.

Full markdown of a documentation page by slug, or a single section of it when `section` (a heading anchor from list_docs or search_docs) is given.

Full-text search across the documentation. Returns matching pages and sections with the slug and section anchor to pass to read_doc, plus a snippet.

Run Archestra, connect your clients, and see your first governed request

Connect your AI client to Archestra's tools, models, and shared skills

Send your first message in Chat and from a connected client, then find both in the logs

Turn a Claude Code project into a shared Archestra agent, with its skills, MCP servers, and hooks

How Archestra Platform is priced and licensed

Build agents with instructions, tools, skills, subagents, and triggers

Stop agents from leaking data, with OpenAPPA policies on every tool call

Cover your tools with rules, change the policy, and sync it with GitHub

Cover an MCP server's tools with a ready-made policy package

Make Guardrails check your client, with built-in support or session headers

Run coding agents and long tasks in their own Kubernetes containers

Prepare Kubernetes nodes, storage, and the Agent Sandbox controller for Agent Runtime

Hand a task from your coding agent to Agent Runtime, then bring the result back

Run your own coding agent image in Agent Runtime

Reusable SKILL.md instruction sets that agents load on demand

Create and edit SKILL.md skills in the UI or from chat

Bring skills in from GitHub, MCP servers, and plugins

Install Archestra skills in your coding agents from one shared marketplace

Client-native extensions for Claude Code, Codex, Copilot CLI, and Cursor

Let an agent delegate work to its own copy, your agents, built-in subagents, or external A2A agents

The system subagents Archestra seeds into every organization, and what each one does

Connect external Agent2Agent systems and use them as subagents

Scripts that run in the sandbox when an agent lifecycle event fires

Start agent runs from webhooks, A2A calls, email, Slack, Microsoft Teams, and Telegram

Call an agent over HTTP with the A2A protocol

Give each agent an email address that runs the agent and replies in the thread

Give each Archestra agent its own Slack bot

Connect Archestra agents to Microsoft Teams channels

Connect Archestra agents to Telegram chats and groups

Add MCP servers once, then give agents and MCP clients their tools through governed gateways

Add MCP servers to your organization's registry, install them, and give their tools to agents and gateways

Configure a remote or self-hosted MCP server and test its connection

Connect a personal account or shared service account to an MCP registry entry

Run MCP server processes in Kubernetes and manage their runtime

One MCP endpoint that gives a client the tools, knowledge, subagents, and skills you choose

How clients sign in to a gateway, and how Archestra signs in to each MCP server

Authenticate a client to an MCP Gateway with OAuth, a platform token, or your identity provider's JWT

Let your own app or service call an MCP Gateway with an OAuth client

Set how Archestra signs in to each MCP server, and whose account each call uses

See and control every model call your company makes, from coding agents to your own apps

How apps, agents, and people sign in to the LLM Proxy, and whose provider key each call uses

Connect provider API keys and personal subscriptions for Chat and the LLM Proxy

Connect Amazon Bedrock with an API key, AWS access keys, or the IAM identity of your Archestra deployment.

Connect Azure model deployments with an API key or Microsoft Entra ID

Connect Claude with an Anthropic API key, Microsoft Foundry, Vertex AI, or workload identity federation.

Connect Gemini using Google AI Studio or Vertex AI.

Connect vLLM, llama.cpp, LM Studio, or another OpenAI-compatible server

Connect an Ollama server and choose its native or OpenAI-compatible transport

Connect the models included in your own GitHub Copilot subscription.

Connect Microsoft 365 Copilot to answer questions using the signed-in user’s work data.

Use another Archestra instance as the upstream model provider

Track LLM spend by team, agent, model, and person, and set usage limits

Call models from multiple providers through an OpenAI-compatible endpoint

Give agents and MCP clients cited answers from connected sources and uploaded documents

Supported knowledge connectors, their setup, and how each one syncs source permissions

Connect Jira documents to Knowledge and configure source access

Connect Confluence documents to Knowledge and configure source access

Connect GitHub documents to Knowledge and configure source access

Connect GitLab documents to Knowledge and configure source access

Connect Asana documents to Knowledge and configure source access

Connect ServiceNow documents to Knowledge and configure source access

Connect Notion documents to Knowledge and configure source access

Connect SharePoint documents to Knowledge and configure source access

Connect OneDrive documents to Knowledge and configure source access

Connect Google Drive documents to Knowledge and configure source access

Connect Dropbox documents to Knowledge and configure source access

Connect Linear documents to Knowledge and configure source access

Connect Outline documents to Knowledge and configure source access

Connect Salesforce documents to Knowledge and configure source access

Connect Web Crawler documents to Knowledge and configure source access

Connect Perforce (Helix Core) documents to Knowledge and configure source access

Connect M-Files documents to Knowledge and configure source access

Upload reference files, control access, and index them into a Knowledge Base

Set the embedding model, search ranking, contextual retrieval, and OCR for Knowledge Bases

Work with agents, files, projects, and apps in Archestra's built-in chat

Keep chats, agent runs, files, instructions, and schedules in one shared workspace

Build interactive apps with an agent, then run, share, and manage them

Deploy Archestra, assign access, connect identity providers, and monitor operations

Install Archestra with Docker or Helm and configure production access

Assign roles and share resources with users, teams, and service accounts

Isolate tools, knowledge, skills, subagents, runtimes, and cost limits across deployment environments

Connect Okta, Microsoft Entra ID, Google, GitHub, GitLab, or any OIDC or SAML provider for sign-in and per-user tool access

Sign users in with their existing identity provider via OIDC or SAML

Map SSO claims to Archestra roles using Handlebars templates

Automatically add and remove users from Archestra teams based on IdP group membership

Per-user identity for downstream MCP tool calls — OBO, ID-JAG, Cross-App Access, and RFC 8693 token exchange

End-to-end setup for Microsoft Entra ID — SSO sign-in plus On-Behalf-Of token exchange for downstream MCP tool calls

End-to-end setup for Okta — SSO sign-in plus Okta-managed token exchange for downstream MCP tool calls

TOTP-based 2FA for member accounts, organization-wide enforcement, and session lifetime controls

Reset any user's password from the shell when there is no email-based recovery

See every model request, tool call, and admin change, and choose who can read them and how long they stay

Export Archestra metrics, traces, logs, and usage events to the monitoring stack you already run

Scrape Archestra's Prometheus metrics and look up every metric name and label

Send OpenTelemetry traces and logs for every LLM call, tool call, and agent run to your collector

Export product-usage events from the Archestra web UI to your own OpenTelemetry collector

Install Archestra's prebuilt Grafana dashboards for LLM usage, MCP tools, agent sessions, and platform health

Reproducible LLM proxy latency measurements with a mock inference upstream

Protect stored credentials and content, and manage encryption keys

Server-side encryption of stored conversation and tool content

Configure external secrets storage for sensitive data

Save credentials once and reuse them across agents, MCP servers, skills, and knowledge

Connect AI clients and agent frameworks to the LLM Proxy and MCP Gateway

Connect Claude Code with subscription or API-key inference

Route Claude Desktop's inference and tools through Archestra

Connect an n8n AI workflow to Archestra

Connect Open WebUI models and tools to Archestra

Route AI SDK model requests through Archestra

Route Pydantic AI model requests through Archestra

Route a Mastra agent through the LLM Proxy

Connect a Foundry agent to Archestra MCP Gateway tools

Propose a change or report a bug through a GitHub issue.

Run Archestra from source with Tilt and a local Kubernetes cluster.

Add a model provider to the LLM Proxy, the Model Router, and the built-in Chat.

Add a connector that syncs an external data source into knowledge bases.

Add a search backend, such as an external index, that stores and ranks knowledge chunks.

Report a security vulnerability in Archestra privately, by email or through a GitHub security advisory.

Look up environment variables, API endpoints, built-in tools, and the Apps SDK

Authenticate platform API requests and explore the endpoint reference.

Every environment variable that configures an Archestra deployment

The window.archestra SDK, styling, security model, and authoring tools for MCP Apps

Built-in MCP server providing tools for managing Archestra platform resources

Built-in role grants, available permissions, and LLM API access requirements