MCP Gateway · Codex
Connect Splunk to Codex
Codex can read your Splunk alerts, saved searches and macros as it changes the code they watch. Engineering teams reach Splunk through the Speakeasy MCP Gateway, which decides per role which Splunk tools each person can call and records every call in one audit log.
- Category
- Infrastructure
- Tools
- 9
- Authentication
- API key
- Codex
- CLI and ChatGPT desktop app
Behind the MCP Gateway
Run Splunk MCP behind the MCP Gateway
One URL for every agent, sign-in through your IdP, RBAC down to the tool, and every Splunk call inspected and logged.
Set up
Add Splunk to Codex in 4 steps
- 01
Add Splunk from the catalog
An admin finds Splunk 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.
Splunk authenticates with an API key. Enter it under Upstream headers in the install dialog, or later on the server's Settings tab. The key is stored on the server, sent with every upstream request, and never reaches anyone's client configuration.
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.
- 02
Choose who can use Splunk
Give teams the
mcp:connectscope on the Splunk server through team access or a role. The organization gateway works out each person's servers from their live access, so granting access adds Splunk to their gateway on the next call, and removing it takes it away. - 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' - 04
Sign in and use Splunk from Codex
The first time Codex connects, it opens a browser so the person can sign in to Speakeasy through your identity provider.
From then on, Splunk'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 Splunk
Review alerts before renaming a field
Before changing a log field, Codex pulls the saved searches, alerts and field extractions so you can find the ones that use it and update them in the same change.
Check the version your scripts target
When an alert setup or deploy script depends on Splunk behavior, Codex reads the instance version and operational status first, so the change targets what is actually running.
Verify a fix in the logs
After a fix ships, Codex runs SPL comparing error counts before and after the deploy and reports whether the errors stopped.
Tools
9 tools
Each Splunk tool can be allowed or denied per team and role at the MCP Gateway before Codex sees it.
splunk_get_info
Get comprehensive information about the Splunk instance. Retrieves system information including version, hardware specs, and operational status.
splunk_get_indexes
Get a list of indexes from Splunk. Indexes are data repositories where machine data is stored and organized.
splunk_get_index_info
Get detailed information about a specific Splunk index. Returns comprehensive configuration and status information for the specified index.
splunk_get_user_list
Get a list of users from Splunk. Retrieves information about all users including authentication details, roles, and account status.
splunk_get_user_info
Retrieves detailed information about the currently authenticated user including roles and permissions. Returns comprehensive user profile data for the current session.
splunk_run_query
Execute a Splunk search query and return the results. This is the primary tool for running Splunk searches using SPL (Search Processing Language). Use this to retrieve log data, perform aggregations, analyze events, and extract insights from your Splunk environment.
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 Splunk call is logged with the person and the client that made it.
Access by role
Gateway
People reach only the Splunk tools their team or role allows.
Request and response blocking
Gateway
A risk policy scoped to Splunk 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
Can Speakeasy block a Splunk call from Codex?
Can the device agent manage Codex's Splunk setup?
How do Codex users get Splunk?
Are Splunk calls from Codex logged?
Connect more