MCP Server

The Inference MCP server lets compatible AI clients query and operate Inference platform resources from your project. Use it to inspect projects, models, datasets, rubrics, evals, training jobs, deployments, inferences, traces, spans, and HALO agent-trace reports without leaving the client. The most common workflow is applying HALO fixes: ask your assistant to apply the suggested fixes for an agent, and it pulls the HALO report and edits your code directly. See Example prompts.

Add the server

Use this URL everywhere:

https://mcp.inference.net/mcp

Or open mcp.inference.net and click a client button. The first request opens a browser. Sign in with your Inference account, pick one project or every project in the team, and leave access on read-only unless you want the agent to create datasets, run evals, launch training, or change deployments. No API key goes in the config.

Read-only is the default. A read grant can browse everything but cannot change resources. Turn on write only when you want MCP tools to mutate the project.

Desktop

Claude Desktop

Open Customize → Connectors.
Add a custom connector with https://mcp.inference.net/mcp.
Click Connect and complete sign-in.

Codex Desktop

Open Settings → MCP servers.
Add a Streamable HTTP server with https://mcp.inference.net/mcp.
Click Authenticate.

ChatGPT

Enable Developer Mode.
Create a custom connector with https://mcp.inference.net/mcp.
Complete the OAuth prompt.

Editors

Claude Code

claude mcp add --transport http inference https://mcp.inference.net/mcp

Complete the browser sign-in when prompted.

Cursor

Click Add to Cursor on mcp.inference.net, or add:

{
  "mcpServers": {
    "inference": {
      "url": "https://mcp.inference.net/mcp"
    }
  }
}

VS Code

{
  "servers": {
    "inference": {
      "type": "http",
      "url": "https://mcp.inference.net/mcp"
    }
  }
}

Codex CLI

codex mcp add inference --url https://mcp.inference.net/mcp

Then authenticate when the client asks.

How access is scoped

OAuth consent binds the connection to one project or every current project in the team, plus either read or read+write. A single-project grant makes project_id optional. A team-wide grant can see every current and future project in that team; tools that need a project then require project_id — call list_projects first.

One project per connection. Pick a single project at consent when you want implicit project_id resolution.
All projects in the team. Pick this when the agent should work across the team. New projects created later are included automatically.
Switching scope. Add the server again and pick a different project or team-wide access at consent. There is no in-session project switch.
Call whoami to see the current team, scoped projects, and permissions.

Header API keys still work for CI and for clients that cannot do OAuth. See Advanced / CI.

Example prompts

You drive the MCP server in natural language. Your assistant picks the right tools and resolves the project from your grant.

Apply HALO fixes for an agent

Apply the HALO suggested fixes for the customer-support-agent.

If you don’t name an agent:

Apply the latest HALO fixes.

Run HALO on demand or on a schedule

Run HALO on the customer-support-agent over the last 24 hours, then apply the fixes.

Create a daily HALO schedule for the customer-support-agent at 9am UTC.
Pause the HALO schedule for the customer-support-agent.

Starting a HALO run and creating a schedule consume credits and compute, and require write access. A schedule fires on its cadence until you pause or archive it. Your assistant should confirm the agent, time window, and prompt before starting.

More examples

What project is this connection scoped to?
List the agents in this project and their execution counts.
Show me the latest HALO runs.
Summarize the errors in the last 50 inferences.
Find the slowest traces from today.
List my training jobs and their status.
Create an eval dataset from successful traffic over the last week.

Read actions work with a read-only grant. Write actions (creating datasets, running evals, launching training jobs, changing deployments) need write access.

Advanced / CI

Clients that cannot run OAuth can still send a project API key.

URL: https://mcp.inference.net/mcp
Authorization: Bearer <your-project-api-key>

export INFERENCE_API_KEY="<your-project-api-key>"

claude mcp add --transport http inference https://mcp.inference.net/mcp \
  --header "Authorization: Bearer $INFERENCE_API_KEY"

codex mcp add inference \
  --url https://mcp.inference.net/mcp \
  --bearer-token-env-var INFERENCE_API_KEY

Create keys on the API Keys page. Keep them out of source control.

Troubleshooting

Error	What it means	How to fix
`401`	No credential, or the token/key is invalid.	Complete browser sign-in, or check `Authorization: Bearer <sk-inference-…>` for CI.
`403`	The grant or key does not have the permission needed.	Re-consent with write, or use a key with write scope.
`Project ID is required`	Session auth, or a multi-project key with no default.	Name the project, or connect with a single-project OAuth grant.
`Project not found`	The requested project is outside this connection.	Re-add the server and pick that project.

Integrations

Traces

Gateway

Add the server

Desktop

Claude Desktop

Codex Desktop

ChatGPT

Editors

Claude Code

Cursor

VS Code

Codex CLI

How access is scoped

Example prompts

Apply HALO fixes for an agent

Run HALO on demand or on a schedule

More examples

Advanced / CI

Troubleshooting

​Add the server

​Desktop

​Claude Desktop

​Codex Desktop

​ChatGPT

​Editors

​Claude Code

​Cursor

​VS Code

​Codex CLI

​How access is scoped

​Example prompts

​Apply HALO fixes for an agent

​Run HALO on demand or on a schedule

​More examples

​Advanced / CI

​Troubleshooting

Add the server

Desktop

Claude Desktop

Codex Desktop

ChatGPT

Editors

Claude Code

Cursor

VS Code

Codex CLI

How access is scoped

Example prompts

Apply HALO fixes for an agent

Run HALO on demand or on a schedule

More examples

Advanced / CI

Troubleshooting