# Splunk MCP connector

The Splunk connector brings Splunk users, roles, outbound ports and IP allowlists to Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent, with every call made as the signed-in person and recorded in an audit log.

Source: https://elaichi.ai/connectors/splunk/

## Facts

| | |
| --- | --- |
| Application | Splunk |
| Category | Observability |
| AI tools | 112 |
| Authentication | Connects with an API key |
| Bring your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Splunk is connected

- List every Splunk role and who holds admin
- Create a Splunk user for the new SRE with the analyst role
- Which IP allowlist entries are set in Splunk right now?

## Connect Splunk in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Splunk.
2. Optionally set Share with, then press Connect.
3. Paste a Splunk API key. One person generates a token in Splunk and pastes it once. Everyone else works through Share with, and never sees it.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Splunk tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Splunk MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Splunk MCP connector for Claude Code

Endpoint: https://api.elaichi.ai/mcp

1. In a terminal, run `claude mcp add` with the endpoint.
2. Start Claude Code and run `/mcp`.
3. Pick elaichi, then sign in and approve in the browser.

```bash
claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
```

Use `--scope project` instead to share it with the repository through `.mcp.json`.

## Splunk MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

## Splunk MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Splunk MCP connector for Microsoft Copilot

Endpoint: https://api.elaichi.ai/mcp

1. In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
2. Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
3. Create a new connection, sign in and approve, then press Add to agent.
4. Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

## Connect Splunk to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Every scope the client asks for starts ticked except "Delete things", which you tick yourself. Calling a Splunk tool needs "Use your connected apps". Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Think hard before granting Use your connected apps, which can also delete in connected apps and cannot be undone.

## What teams do with Splunk through Elaichi

### Set up a new engineer in Splunk

IT. Create the Splunk user from a chat, give them the right role, and confirm the account exists before their first day. No one has to open the admin console.

### Review who holds the admin role

Security. Ask for every Splunk role and the users attached to it, then spot the people who still have more access than they need.

### Open an outbound port for a new destination

Platform. Add the outbound port Splunk needs to reach a new forwarding target, list what is already open, and remove ports nobody uses any more.

### Add an office address to the allowlist

Networking. When a site moves or a VPN changes, add the new IP allowlist entry in Splunk and clear the old ones in one go.

### Pull the user and role list for an audit

Compliance. Get a current list of Splunk users and their roles as a plain summary you can hand to an auditor without exporting anything by hand.

### Fix a user who cannot see their data

Helpdesk. Look up the Splunk user by name, check which role they hold, and update it so they can get back to work.

## Elaichi vs Zapier MCP vs Composio for Splunk

All three can connect Splunk to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Splunk tools | Allow or restrict single Splunk tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Splunk call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Splunk to Claude?

Connect Splunk in Elaichi first by pasting a Splunk API key, which is the only sign-in step Splunk asks for. There is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Sign in as yourself and Splunk is ready to use.

### Does Splunk work with ChatGPT and Cursor as well as Claude?

Yes. Once Splunk is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client and the Elaichi Agent. You connect Splunk once and every client picks it up.

### What can an AI agent actually do with my Splunk data?

With Splunk connected, an agent can list, create, update and delete Splunk users and roles, manage outbound ports, and add or remove IP allowlist entries. You can ask who holds the admin role, set up a new user with the right role, or add an office address to the allowlist. Short, concrete asks like "list Splunk roles" work better than long paragraphs.

### Does connecting Splunk give the AI every user, role and setting?

No. Every call to Splunk runs as the person who signed in, so the agent can only reach the users, roles, ports and allowlists that person's own Splunk access permits. Elaichi can narrow that access further with roles and restrictions, and it never widens it.

### Can my team share one Splunk connection?

Yes. One person connects Splunk with an API key and shares the connection with a team, and nobody else ever handles the key. Each teammate still signs in to Elaichi as themselves, so the audit log names the actual person behind every change in Splunk.

### Can I stop an agent from deleting or changing things in Splunk?

Yes. Restrictions in Elaichi apply per action, so you can restrict deleting Splunk users or changing roles for a role or for one person while leaving listing and lookups open. A restricted action still appears in Elaichi's tool search, flagged as restricted, but no client can run it whatever the prompt says.

### What happens to a Splunk connection when someone leaves?

Offboarding a person in Elaichi ends their access to Splunk through every client at once. A shared Splunk connection keeps working for everyone else on the team. If you ever need to remove Splunk entirely, disconnecting it once in Elaichi removes it from every client.

### Does the Splunk MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Splunk is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Splunk?

Yes. Both let Claude, ChatGPT or Cursor use Splunk. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Splunk call.

### How is Elaichi different from Composio for Splunk?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Splunk: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 112 Splunk tools

Every tool below is callable through https://api.elaichi.ai/mcp once Splunk is connected, subject to the toolbox it is in and the restrictions on the caller.

- **List all Splunk users** (List). List Splunk Cloud users on the stack (GET /{stack}/adminconfig/v2/users, Admin Config Service). Returns name, email, fullName, roles, defaultApp, lockedOut, lastSuccessfulLogin. Paginated with count/offset (max 100 per page). Users are local to the search head the token was created on.
- **Get single Splunk user by ID** (Get). Get one Splunk Cloud user (GET /{stack}/adminconfig/v2/users/{userName}). The id is the user name (login). Returns name, email, fullName, roles, capabilities, defaultApp, lockedOut, lastSuccessfulLogin.
- **Create a Splunk user** (Create). Create a new user. Splunk Cloud Admin Config Service (POST /users). Required: name, password. The optional Federated-Search-Manage-Ack header (only needed when granting fsh_manage) is not sent.
- **Update a Splunk user by ID** (Update). Modify a specific user on the stack. Splunk Cloud Admin Config Service (PATCH /users/{userName}). The id is the userName. Required: id. The optional Federated-Search-Manage-Ack header (only needed when granting fsh_manage) is not sent.
- **Delete a Splunk user by ID** (Delete). Delete a specific user. Splunk Cloud Admin Config Service (DELETE /users/{userName}). The id is the userName. Required: id.
- **List all Splunk roles** (List). List Splunk Cloud roles on the stack (GET /{stack}/adminconfig/v2/roles). Returns each role name with its capabilities, imported roles, default app, search indexes and quotas. Paginated with count/offset (max 100 per page).
- **Get single Splunk role by ID** (Get). Get one Splunk Cloud role (GET /{stack}/adminconfig/v2/roles/{roleName}). The id is the role name, e.g. sc_admin or user. Returns capabilities, imported roles, default app, allowed/default search indexes and search job quotas.
- **Create a Splunk role** (Create). Create a new role on the stack. Splunk Cloud Admin Config Service (POST /roles). The optional Federated-Search-Manage-Ack header (only needed when adding fsh_manage) is not sent.
- **Update a Splunk role by ID** (Update). Modify a specific role on the stack. Splunk Cloud Admin Config Service (PATCH /roles/{roleName}). The id is the roleName. Required: id. The optional Federated-Search-Manage-Ack header (only needed when adding fsh_manage) is not sent.
- **Delete a Splunk role by ID** (Delete). Delete a specific role. Splunk Cloud Admin Config Service (DELETE /roles/{roleName}). The id is the roleName. Required: id.
- **List all Splunk outbound ports** (List). Describe the outboundports with ports and subnets. Splunk Cloud Admin Config Service (GET /access/outbound-ports).
- **Create a Splunk outbound port** (Create). Add subnets to the outboundports for the feature, if they don't already exist. Splunk Cloud Admin Config Service (POST /access/outbound-ports).
- **Get single Splunk outbound port by ID** (Get). Describe the outboundports with ports and subnets. Splunk Cloud Admin Config Service (GET /access/outbound-ports/{port}). The id is the port. Required: id.
- **Delete a Splunk outbound port by ID** (Delete). Delete an existing outbound port if it exists, from where the feature is accessible from. Splunk Cloud Admin Config Service (DELETE /access/outbound-ports/{port}). The id is the port. Required: id.
- **List all Splunk outbound ports v 6** (List). List the outboundports with ports and ipv6 subnets. Splunk Cloud Admin Config Service (GET /access/outbound-ports-v6).
- **Create a Splunk outbound ports v 6** (Create). Add ipv6 subnets to the outboundports for the feature, if they don't already exist. Splunk Cloud Admin Config Service (POST /access/outbound-ports-v6).
- **Get single Splunk outbound ports v 6 by ID** (Get). Describe the outboundports with ports and ipv6 subnets. Splunk Cloud Admin Config Service (GET /access/outbound-ports-v6/{port}). The id is the port. Required: id.
- **Delete a Splunk outbound ports v 6 by ID** (Delete). Delete an existing ipv6 outbound port if it exists, from where the feature is accessible from. Splunk Cloud Admin Config Service (DELETE /access/outbound-ports-v6/{port}). The id is the port. Required: id.
- **List all Splunk IP allowlists** (List). Describe the allowlist with its status and subnets from where the feature is accessible from. Splunk Cloud Admin Config Service (GET /access/{feature}/ipallowlists). Required: feature.
- **Create a Splunk IP allowlist** (Create). Add subnets to the allowlist for the feature, if they don't already exist. Splunk Cloud Admin Config Service (POST /access/{feature}/ipallowlists). Required: feature.
- **Splunk IP allowlists bulk delete** (Delete). Delete existing ip subnets (if they exists) from where the splunk cloud stack feature is accessible from. Splunk Cloud Admin Config Service (DELETE /access/{feature}/ipallowlists). Required: feature.
- **Delete a Splunk IP allowlist by ID** (Delete). Delete an existing ip subnet if it exists, from where the feature is accessible from. Splunk Cloud Admin Config Service (DELETE /access/{feature}/ipallowlists/{subnet}). The id is the subnet (URL-encode CIDR slashes, e.g. 10.0.0.0%2F24). Required: id, feature.
- **List all Splunk IP allowlists v 6** (List). Describe the allowlist with its status and ipv6 subnets from where the feature is accessible from. Splunk Cloud Admin Config Service (GET /access/{feature}/ipallowlists-v6). Required: feature.
- **Create a Splunk IP allowlists v 6** (Create). Add ipv6 subnets to the allowlist for the feature, if they don't already exist. Splunk Cloud Admin Config Service (POST /access/{feature}/ipallowlists-v6). Required: feature.
- **Splunk IP allowlists v 6 bulk delete** (Delete). Delete existing ipv6 subnets (if they exists) from where the splunk cloud stack feature is accessible from. Splunk Cloud Admin Config Service (DELETE /access/{feature}/ipallowlists-v6). Required: feature.
- **Delete a Splunk IP allowlists v 6 by ID** (Delete). Delete an existing ipv6 subnet if it exists, from where the feature is accessible from. Splunk Cloud Admin Config Service (DELETE /access/{feature}/ipallowlists-v6/{subnet}). The id is the subnet (URL-encode CIDR slashes, e.g. 10.0.0.0%2F24). Required: id, feature.
- **List all Splunk apps** (List). List apps available on the stacks. Splunk Cloud Admin Config Service (GET /apps). Paginated with count/offset (max 100).
- **Splunk apps install private** (Action). Install an app. Splunk Cloud Admin Config Service (POST /apps). Required: truto_acs_legal_ack, truto_x_splunk_authorization. Private app: upload the .tar.gz/.spl package (multipart field "package"); requires ACS-Legal-Ack (Y) and an AppInspect token (X-Splunk-Authorization).
- **Splunk apps install splunkbase** (Action). Install an app. Splunk Cloud Admin Config Service (POST /apps). Required: truto_acs_legal_ack, truto_x_splunkbase_authorization, truto_acs_licensing_ack. Splunkbase app: set splunkbase=true and send splunkbaseID (and optional version); requires a Splunkbase session ID (X-Splunkbase-Authorization) and ACS-Licensing-Ack (the app license URL).
- **Get single Splunk app by ID** (Get). Get an app. Splunk Cloud Admin Config Service (GET /apps/{app}). The id is the app. Required: id.
- **Update a Splunk app by ID** (Update). Update an installed splunkbase apps. Splunk Cloud Admin Config Service (PATCH /apps/{app}). The id is the app. Required: id, truto_x_splunkbase_authorization, truto_acs_licensing_ack.
- **Delete a Splunk app by ID** (Delete). Uninstall the app. Splunk Cloud Admin Config Service (DELETE /apps/{app}). The id is the app. Required: id.
- **List all Splunk victoria apps** (List). List apps available on the stacks. Splunk Cloud Admin Config Service (GET /apps/victoria). Paginated with count/offset (max 100).
- **Splunk victoria apps install private** (Action). Install an app for Victoria stack. Splunk Cloud Admin Config Service (POST /apps/victoria). Required: truto_x_splunk_authorization, truto_acs_legal_ack. Private app on Victoria Experience: requires ACS-Legal-Ack (Y) and an AppInspect token (X-Splunk-Authorization).
- **Splunk victoria apps install splunkbase** (Action). Install an app for Victoria stack. Splunk Cloud Admin Config Service (POST /apps/victoria). Required: truto_x_splunkbase_authorization, truto_acs_licensing_ack. Splunkbase app on Victoria Experience: set splunkbase=true and send splunkbaseID; requires a Splunkbase session ID and ACS-Licensing-Ack (the app license URL).
- **Get single Splunk victoria app by ID** (Get). Get an app. Splunk Cloud Admin Config Service (GET /apps/victoria/{app}). The id is the app. Required: id.
- **Update a Splunk victoria app by ID** (Update). Update an installed splunkbase apps. Splunk Cloud Admin Config Service (PATCH /apps/victoria/{app}). The id is the app. Required: id, truto_x_splunkbase_authorization, truto_acs_licensing_ack.
- **Delete a Splunk victoria app by ID** (Delete). Uninstall the app. Splunk Cloud Admin Config Service (DELETE /apps/victoria/{app}). The id is the app. Required: id.
- **Splunk victoria apps export** (Export). Fetch the app data and returns the selected contents as a tar file. Splunk Cloud Admin Config Service (GET /apps/victoria/export/download/{app}). Required: app.
- **List all Splunk capabilities** (List). List capabilities. Splunk Cloud Admin Config Service (GET /capabilities).
- **List all Splunk managed glue resources** (List). Describe cloud resources managed resources. Splunk Cloud Admin Config Service (GET /cloud-resources/managed-glue-resources).
- **Splunk managed glue resources replace** (Action). Add cloud resource permissions for a set of federated providers. Splunk Cloud Admin Config Service (PUT /cloud-resources/managed-glue-resources).
- **List all Splunk self storage buckets** (List). List all configured self storage locations on the stack. Splunk Cloud Admin Config Service (GET /cloud-resources/self-storage-locations/buckets). Paginated with count/offset (max 100).
- **Create a Splunk self storage bucket** (Create). Create self storage location on the stack. Splunk Cloud Admin Config Service (POST /cloud-resources/self-storage-locations/buckets). Required: title, bucketName.
- **Get single Splunk self storage bucket by ID** (Get). Describe a configured self storage location on the stack. Splunk Cloud Admin Config Service (GET /cloud-resources/self-storage-locations/buckets/{bucketPath}). The id is the bucketPath. Required: id.
- **Splunk self storage buckets get policy** (Get). Get the IAM policy to configure S3 bucket for self storage location. Splunk Cloud Admin Config Service (GET /cloud-resources/self-storage-locations/buckets/{bucketName}/policy). Required: bucket_name.
- **Splunk self storage configs get azure consent URL** (Get). Get the URL for admin consent in Microsoft Entra ID (formerly Azure AD). If the tenantId query parameter is provided, the endpoint returns a fully qualified URL, ready to use. Otherwise, the URL contains a {tenant_id} placeholder that the caller must replace. Splunk Cloud Admin Config Service (GET /cloud-resources/self-storage-locations/configs/azure-consent-url).
- **Splunk self storage configs get azure service principal** (Get). Get the Application (client) ID of the Azure service principal used by Splunk Cloud Platform for DDSS. Splunk Cloud Admin Config Service (GET /cloud-resources/self-storage-locations/configs/azure-service-principal).
- **Splunk self storage configs get prefix** (Get). Get the bucket prefix required to configure self storage location(s). Splunk Cloud Admin Config Service (GET /cloud-resources/self-storage-locations/configs/prefix).
- **Splunk self storage configs get service accounts** (Get). Get the service account for GCS bucket required to configure self storage location(s). Splunk Cloud Admin Config Service (GET /cloud-resources/self-storage-locations/configs/service-accounts).
- ...and 62 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.
