Gives AI agents one governed gateway to enterprise MCP servers, with role-based access, real-time policy enforcement, and usage tracking.
Also known as speakeasy-api/gram, gram
- Stars
- 278
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Nov 14, 2026
- License
- AGPL-3.0
What is Speakeasy Control Plane MCP?
Speakeasy Control Plane gives AI agents one governed gateway to enterprise MCP servers, with role-based access, real-time policy enforcement, and usage tracking.
Summary generated from the project's README
About Speakeasy Control Plane MCP server
Managing enterprise-wide AI agent access and security is the primary function of Speakeasy Control Plane. It acts as a central gateway for connecting agents to various MCPs, skills, and assistants while enforcing fine-grained permissions through role-based access control and OAuth2.1. Organizations can use it to govern how tools interact with internal systems and SaaS vendor APIs.
Administrators use the platform to monitor token usage, track costs, and inspect every prompt and response in real time. The system provides threat detection to block sensitive data or PII and prevents prompt injection. It integrates with enterprise identity providers like Okta, Azure AD, and Google Workspace to sync user roles.
Developers can run the environment locally using a zero script with Docker and Mise dependencies. The platform supports popular AI providers including Claude, ChatGPT, Gemini, and Cursor. It provides visibility into tool effectiveness and allows for the creation of budgets to manage expensive sessions.
What you can do with it
- 1Enforce enterprise security policiesPrevent sensitive data leaks by automatically redacting or blocking PII before it leaves your environment.
- 2Monitor AI operational costsTrack how much your teams are spending on AI by measuring token usage and session costs.
- 3Centralize tool distributionManage which employees have access to specific MCPs and plugins based on their corporate roles.
- 4Detect and prevent prompt injectionUse real-time inspection to identify and stop malicious attempts to manipulate your AI agents.
Written from the project's README. Every use case is checked against a quote from it.
How to install Speakeasy Control Plane MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Speakeasy Control Plane MCP in Claude Code
$ claude mcp add --transport http gram https://ai.speakeasy.com/platform-mcpInstall Speakeasy Control Plane MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"gram": {
"url": "https://ai.speakeasy.com/platform-mcp"
}
}
}Install Speakeasy Control Plane MCP in VS Code
.vscode/mcp.json
{
"servers": {
"gram": {
"type": "http",
"url": "https://ai.speakeasy.com/platform-mcp"
}
}
}Install Speakeasy Control Plane MCP in VS Code CLI
$ code --add-mcp '{"name":"gram","type":"http","url":"https://ai.speakeasy.com/platform-mcp"}'Install Speakeasy Control Plane MCP in Codex
$ codex mcp add gram --url https://ai.speakeasy.com/platform-mcpInstall Speakeasy Control Plane MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.gram] url = "https://ai.speakeasy.com/platform-mcp"
Install Speakeasy Control Plane MCP in Gemini CLI
$ gemini mcp add -s user --transport http gram https://ai.speakeasy.com/platform-mcpInstall Speakeasy Control Plane MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"gram": {
"url": "https://ai.speakeasy.com/platform-mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablespeakeasy-api/gram is public and reachablegithub.com/speakeasy-api/gram ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)AGPL-3.0spdx.org/licenses/AGPL-3.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/speakeasy-api/gram ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubIntroduction
Speakeasy Control Plane helps your organization connect, secure, and manage MCPs, Skills, and Assistants. It provides fine-grained permissions, threat detection, and visibility into token use and costs. Tool calls, permission changes, and access events are logged and searchable. The platform is SOC 2 Type II and ISO 27001 certified.
Naming note: The product is now called Speakeasy Control Plane. It was previously called Gram, and this GitHub repository has not yet been renamed (speakeasy-api/gram).
To get started on the hosted platform, sign up or read the getting started guide.
Supports popular AI providers
Observe
Track AI usage across teams and measure impact with either tokens or cost. Deep dive expensive sessions, create budgets and measure tool effectiveness. Built on a foundation of Opentelemetry. Exportable and interactive via platform MCP and a built in assistant.
Secure
Every prompt, response, and agent action is inspected and enforced in real time. Sensitive data is blocked, redacted, or logged before it leaves your environment. Create and enforce flexible policies to prevent prompt injection, log shadow use and detect PII secrets and other sensitive data types.
Connect
A single control layer for connecting your agents to MCPs for your SaaS vendors, APIs, and internal systems, with policy enforcement and granular access control built in. Private networking and tunneling deployed on demand.
Distribute
Centralise distribution of MCPs, Skills, Plugins and Assistants to your team based on enterprise roles. Team, server, and tool level permissions enforced through RBAC and Oauth2.1. Synced to your enterprise IDP (Okta, Azure AD, Google Workspace, etc.).
Support
- Chat with us: Join our slack for support and discussions or email us at support@speakeasy.com.
- Contribute feature requests or report issues on our roadmap.
- Read the Speakeasy Control Plane documentation.
Running locally
Run ./zero until it succeeds. This script is what you use to run the dashboard and services for local development. It installs dependencies, runs pending database migrations, and starts everything up.
The main dependencies are Mise and Docker. The ./zero script will guide you to install these if they are not found.
Seed your local organization with a realistic working environment — a deployed API, agent sessions, telemetry, risk findings, teammates, and an API key:
mise seed
It talks to the databases directly, so it can run before the services are up, and re-running it resets the seeded data.
To work on several branches at once, each git worktree can run its own full stack on its own ports:
wt switch --create my-feature
See CONTRIBUTING.md for more detail on local development, auth, worktrees, and the CLI.
Contributing
Contributions are welcome! Please open an issue or discussion for questions or suggestions before starting significant work.
See CONTRIBUTING.md for development setup and detailed contribution guidelines.
Tech Stack
- TypeScript — dashboard language.
- Golang — backend language.
- Goa — design-first API framework.
- Temporal — workflow engine.
- Polar — usage-based billing.
- OpenRouter — LLM gateway.
- Speakeasy — generated SDKs. Spec hosted here.
Contributors
Speakeasy Control Plane MCP questions
How do I add Speakeasy Control Plane MCP to Claude Code?
Run claude mcp add --transport http gram https://ai.speakeasy.com/platform-mcp in your terminal. Add --scope user to make it available in every project.
How do I add Speakeasy Control Plane MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Does Speakeasy Control Plane sync with my identity provider?
Yes. It provisions access by role from your enterprise IdP, including Okta, Azure AD, and Google Workspace.
How does it enforce security policies on agent actions?
It inspects every prompt, response, and agent action in real time, blocking, redacting, or logging sensitive data before it leaves your environment.
Can I track token usage and costs across teams?
Yes, you can track AI usage by tokens or cost, drill into expensive sessions, and set budgets, with data exportable via OpenTelemetry.
Which AI clients are supported?
It works with Claude, Claude Code, ChatGPT, Codex, Gemini, Cursor, and GitHub Copilot.
What permissions model does it use?
Permissions are enforced at team, server, and tool level through RBAC and OAuth2.1.