Skip to main content
Back to the Hugging Face MCP server

MCP Gateway · Codex

Hugging Face icon

Connect Hugging Face to Codex

Evaluation work depends on picking the right datasets and keeping up with library changes. Through the Speakeasy MCP Gateway, Codex can look up Hub datasets and fetch current Hugging Face documentation while it writes eval harnesses and migrations. Engineers sign in with your identity provider, and Speakeasy can deny any Codex tool call before it runs.

Category
AI & search
Tools
10
Authentication
OAuth
Codex
CLI and ChatGPT desktop app

Behind the MCP Gateway

Run Hugging Face MCP behind the MCP Gateway

One URL for every agent, sign-in through your IdP, RBAC down to the tool, and every Hugging Face call inspected and logged.

Deploy on MCP Gateway

Set up

Add Hugging Face to Codex in 4 steps

  1. 01

    Add Hugging Face from the catalog

    An admin finds Hugging Face in the MCP Catalog (MCP Gateway > MCP > Catalog) and clicks Add. Speakeasy registers the vendor's server as a remote MCP server and proxies sessions to it. Nothing is copied or re-hosted.

    Hugging Face uses OAuth. Servers that support dynamic client registration get their OAuth configuration applied automatically.

    Where MCP-scoped policies are enabled, the install offers a recommended risk policy for the new server that detects secrets and PII and inspects tool requests and responses.

  2. 02

    Choose who can use Hugging Face

    Give teams the mcp:connect scope on the Hugging Face server through team access or a role. The organization gateway works out each person's servers from their live access, so granting access adds Hugging Face to their gateway on the next call, and removing it takes it away.

  3. 03

    Connect Codex

    Add the gateway as an MCP server, then log in.

    Run the first command with your organization gateway URL.

    Run the second command to sign in.

    codex mcp add 'speakeasy' \
      --url 'https://<organization host>/mcp/gateway/<organization slug>'
    codex mcp login 'speakeasy'
  4. 04

    Sign in and use Hugging Face from Codex

    The first time Codex connects, it opens a browser so the person can sign in to Speakeasy through your identity provider.

    Hugging Face needs its own OAuth grant, so each person connects it once. Until they do, Hugging Face calls fail while the rest of the gateway keeps working.

    From then on, Hugging Face's tools appear in Codex, limited to what the person's access allows, and every call lands in the gateway's tool logs.

To roll it out to a team, a ChatGPT workspace admin imports the plugin marketplace under Admin > Plugins and sets an installation policy per role. Imported plugins reach nobody until a policy is set.

Use cases

What Codex users do with Hugging Face

Pick datasets for an eval

Codex searches the Hub for datasets that match your task, reads the details of each candidate, and wires the chosen one into the evaluation script.

hub_repo_searchhub_repo_details

Migrate to a newer library API

When a Transformers or Gradio upgrade breaks the build, Codex fetches the documentation for the changed API, reading long pages in chunks, and updates each call site.

hf_doc_fetchhf_doc_search

Check a model's repository details

Before a pinned model goes into production, Codex pulls its repository details so the pull request description records exactly what is being deployed.

hub_repo_details

Tools

10 tools

Each Hugging Face tool can be allowed or denied per team and role at the MCP Gateway before Codex sees it.

hf_whoami

Hugging Face tools are being used by the authenticated user

hub_repo_details

Get details for one or more Hugging Face repos (model, dataset, or space). Auto-detects type unless specified.

See all 10 tools

Control

What Speakeasy can see and stop in Codex

The gateway covers every client the same way. The rest depends on what Codex exposes to Speakeasy.

Tool logs

Gateway

Every Hugging Face call is logged with the person and the client that made it.

Access by role

Gateway

People reach only the Hugging Face tools their team or role allows.

Request and response blocking

Gateway

A risk policy scoped to Hugging Face can reject a tool request before it reaches the server, or withhold a result from Codex. MCP-scoped policies are enabled per organization.

Prompt and tool-call blocking

Codex

Agent hooks send each prompt and tool call to Speakeasy, which allows or denies it before Codex runs it.

User attribution

Codex

An [otel] block in ~/.codex/config.toml sends telemetry to Speakeasy. Export is off by default.

Budgets

Codex

Spend limits can block Codex traffic once a budget is reached.

Device agent and MDM

Codex

The device agent keeps Codex's configuration in sync on managed laptops.

  • Codex cloud tasks and GitHub code review run off the device. Neither the plugin nor OpenTelemetry covers them; OpenAI's Compliance Logs record them after the fact.
  • The workspace rollout needs a ChatGPT Business, Enterprise or Edu admin.

Questions

Frequently asked questions

Does Speakeasy see Hugging Face calls from Codex cloud tasks?
No. Codex cloud tasks run off the device, so neither the plugin nor OpenTelemetry covers them. OpenAI's Compliance Logs record them after the fact.
Can Codex write to Hugging Face repositories?
The catalog's Hugging Face tools search and read models, datasets, Spaces, papers and docs, and run Space tasks. None of them is described as creating or changing a repository.
How do Codex users get Hugging Face?
An admin adds Hugging Face from the Speakeasy MCP Catalog and grants access by team or role. Add the gateway as an MCP server, then log in. Each person then sees only the Hugging Face tools their access allows.
Are Hugging Face calls from Codex logged?
Yes. Hugging Face calls go through the MCP Gateway, which logs each tool call and attributes it to the person and the client that made it.

Connect more

Hugging Face in other clients

AI everywhere.

Control here.