About mtdt — Salesforce DevOps
mtdt provides an MCP server for Salesforce DevOps, for agents and development teams deploying metadata between Salesforce orgs. It includes pre-deployment checks, test validation, and server-side waiting for long-running deploys, while respecting team roles and approval requirements.
Key features
- 01Browse orgs and retrieve metadata
- 02Create and run metadata deployments
- 03Check impact and permissions before deployment
- 04Validate with tests and quick-deploy
- 05Await deployment status without busy polling
Use cases
- 01Promote changes between Salesforce orgs
- 02Deploy local SFDX or Metadata API packages
- 03Run pre-deployment checks and test validation
- 04Investigate failed deployments
MCP support
It provides a remote MCP server over Streamable HTTP and OAuth 2.0, exposing tools for Salesforce orgs, metadata retrieval, deployments, validation, and status checks. Deploy actions require the mtdt:deploy consent scope and follow team roles and approval gates.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.mtdt.ioclaude mcp add --transport http io-mtdt-mtdt https://mcp.mtdt.io{"mcpServers":{"io-mtdt-mtdt":{"type":"http","url":"https://mcp.mtdt.io"}}}Open in Cursor{"servers":{"io-mtdt-mtdt":{"type":"http","url":"https://mcp.mtdt.io"}}}Open in VS Code{"mcpServers":{"io-mtdt-mtdt":{"type":"http","url":"https://mcp.mtdt.io"}}}{"mcpServers":{"io-mtdt-mtdt":{"serverUrl":"https://mcp.mtdt.io"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEmtdt — MCP server for your AI agent
Salesforce DevOps in any MCP-capable coding agent. One remote endpoint:
https://mcp.mtdt.io
Streamable HTTP + OAuth 2.0 (browser sign-in, Dynamic Client Registration) — no API keys, no tokens to copy. Works with Claude Code, Cursor, OpenAI Codex, OpenCode, and anything else that speaks MCP.
What your agent gets
Deploy metadata between Salesforce orgs through mtdt.io: list orgs, create
deployments, browse/retrieve metadata, pre-deploy checks (impact analysis, target conflicts,
profile & permission warnings, record-backup recommendations), Apex test recommendations,
validate with tests, quick-deploy. A zip the agent already has (SFDX project or Metadata API
package) can be uploaded straight to mtdt and deployed whole. Long-running deploys are awaitable
server-side (await_deploy_status) so your agent doesn't busy-poll.
Deploy-capable tools require the Run (mtdt:deploy) consent scope and always respect your
team's mtdt roles — approval-gated targets stay approval-gated.
Claude Code plugin — connection + built-in skills
The plugin is more than the connection: it ships the deployment know-how as skills, so Claude doesn't just have the tools — it knows the playbook.
mtdt-deploy— the full promotion workflow: resolve the target safely (production targets get confirmed, never assumed), browse & pick components, the pre-flight battery (the same checks a human gets in the Deploy modal), validation-first flow, quick-deploy, deploying a local zip, and the guardrails: the 75% coverage rule, rollback snapshots, approval gates.mtdt-troubleshoot— reading failed runs: component vs test vs coverage failures, quick-deploy prerequisites and expiry, stuck retrievals, auth pitfalls — each with the fix, not just the diagnosis.
/plugin marketplace add mtdt-io/mcp
/plugin install mtdt@mtdt
On first use Claude Code opens your browser to sign in to mtdt (OAuth) — no config files.
Connect (any MCP client)
Verified copy-paste configs per client (and the type-field gotchas between them):
CONNECT.md. Every client receives the deployment playbook at connection time
(MCP instructions) and can pull the mtdt-deploy / mtdt-troubleshoot prompts; the plugin
above ships the same know-how as skills, applied without being asked.
Quick versions:
| Client | One-liner |
|---|---|
| Claude Code | claude mcp add --transport http mtdt https://mcp.mtdt.io |
| Cursor |  |
| OpenAI Codex | codex mcp add mtdt --url https://mcp.mtdt.io |
| OpenCode | "mcp": { "mtdt": { "type": "remote", "url": "https://mcp.mtdt.io" } } |
Notes
- Requires an mtdt.io account with at least one connected Salesforce org.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.