Elasticsearch + Muse
How to connect Elasticsearch to Muse
Set up Elasticsearch for Muse with Agent200, then check which tools are available to your agent.
On this page
Overview
This guide connects Elasticsearch to Muse through Agent200's MCP server. When you finish, Muse can search, read and act in Elasticsearch with the tools Agent200 provides, whenever a request needs them.
You add one MCP server to Muse with your Agent200 API key. Your Elasticsearch account is connected through managed OAuth: you approve access once on Elasticsearch's own page, and Agent200 keeps the connection working.
- Connector
- Elasticsearch
- Works with
- Muse ยท Agent app, through MCP
- Authentication
- Managed OAuth, per end user
- You need
- An Agent200 API key
- Tools
- 6 tools
- MCP server
https://api.agent200.com/mcp/
Before you start
- An Agent200 API key. Create one on the API keys page of the dashboard.
- Elasticsearch enabled for your project. In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- An end user with a Elasticsearch account. They approve access once, on Elasticsearch's own page.
- Muse, with custom MCP servers allowed. Muse creates custom connectors from a chat, and your key goes into its secure credentials sheet, never into the chat. Muse Code reads servers from its settings file.
Connect Elasticsearch to Muse
-
1
Step 1: Create your Agent200 API key
Open the API keys page in the Agent200 dashboard and choose Create an API key. You add it to Muse in the next step, as "Authorization: Bearer <your key>". One key covers Elasticsearch and every other connector enabled for your project. Keep it out of chats and source control.
-
2
Step 2: Ask Muse to create a custom connector
Start a new Muse chat and send this message. Muse builds the connector and shows a button to add your API key.
Muse chatMCP: message that asks Muse to create the custom connector Create a Custom Connector for the Agent200 remote MCP server and connect to it: Name: Agent200 Transport: remote streamable HTTP URL: https://api.agent200.com/mcp/ Auth: API key sent in the Authorization header as "Bearer <key>" Open the secure credentials store so I can enter the API key there, not in this chat. Then list its tools to confirm the connection works. -
3
Step 3: Add your key in the secure sheet
Tap the button Muse shows to open Add custom connector, paste your Agent200 API key and tap Add. Muse keeps it in its Secure Credentials Store and lists the Agent200 tools once the connection works.
-
4
Step 4: Using Muse Code? Add the server to its settings
In the terminal version, declare the server in
~/.config/muse/settings.jsonand exportAGENT200_API_KEYin your shell instead of writing the key in the file. Run/mcpin a session to see it.~/.config/muse/settings.jsonMCP: Muse Code settings.json entry { "schema_version": 1, "mcp_servers": { "agent200": { "transport": "streamable_http", "url": "https://api.agent200.com/mcp/", "headers": { "Authorization": "Bearer ${AGENT200_API_KEY}" }, "enabled": true, "mode": "optional" } } } -
5
Step 5: Connect your Elasticsearch account
The first time you ask Muse for something in Elasticsearch, Agent200 returns an authorization link. Open it and approve access on Elasticsearch's own page. Agent200 stores the connection and keeps it working; your password never reaches Muse or Agent200.
Test your connection
Run one request to check everything is wired up.
Ask
Ask Muse to list the Agent200 tools available for Elasticsearch, including which are read-only.
What should come back
- A list of the Elasticsearch tools enabled for this Agent200 project, with their names and descriptions. If no tools appear, check that the connector is available to the project and its tools are enabled.
If no tools appear, check your Agent200 project access for Elasticsearch and make sure its tools are enabled. Tool availability depends on your project setup.
Get your API key
Create a key in the Agent200 dashboard. It reaches Elasticsearch and every other connector enabled for your project.
Instructions for AI agents
Using a coding agent? Paste this brief into it, or give it the address of this page. It lists what to do, in order, to connect Elasticsearch to Muse.
Goal: connect Elasticsearch to Muse with Agent200, through its MCP server. Guide: https://www.agent200.com/connectors/elasticsearch/framework/muse/ 1. The user needs an Agent200 API key. If they have none, send them to https://agent200.com/platform/apikeys/ to choose "Create an API key". They paste it into Muse's settings themselves: never ask for it in chat and never write it into files you share. 2. Make sure Elasticsearch is enabled for their project in the Agent200 dashboard (Connectors), with the tools the task needs. 3. Add Agent200's MCP server to Muse: URL https://api.agent200.com/mcp/, transport streamable HTTP, header "Authorization: Bearer <the user's Agent200 API key>". Follow the setup steps on the guide page for Muse's exact menus or commands. 4. The first Elasticsearch request returns an authorization link if the user has not connected Elasticsearch yet: show it to them and continue once they have approved access on Elasticsearch's own page. 5. Check it works with this request: "Ask Muse to list the Agent200 tools available for Elasticsearch, including which are read-only." What should come back: - A list of the Elasticsearch tools enabled for this Agent200 project, with their names and descriptions. If no tools appear, check that the connector is available to the project and its tools are enabled. 6. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in Elasticsearch, then retry.
The whole guide is also available as Markdown, for agents and LLMs: /connectors/elasticsearch/framework/muse.md
Elasticsearch tools Muse can call
-
List indices
Readelasticsearch_list_indicesList the indices in the cluster with their size and health.
-
Get a mapping
Readelasticsearch_get_mappingGet the field mapping of an index.
-
Search
Readelasticsearch_searchRun a search query against an index.
-
Get a document
Readelasticsearch_get_documentGet a document by its ID.
-
Index a document
Writeelasticsearch_index_documentAdd or replace a document in an index.
-
Delete a document
Writeelasticsearch_delete_documentDelete a document by its ID.
No tool matches that search.
How it works
-
01
You ask Muse
In your own words, for something in Elasticsearch.
-
02
Muse picks a tool
It sees the Elasticsearch tools on the Agent200 MCP server and calls the one the request needs.
-
03
Agent200 runs the call
With your own Elasticsearch connection, within the tools and scopes your project allows.
-
04
Muse answers
It gets the result back from the MCP server and uses it in its reply or its next step.
Each user's own connection. Connections belong to individual end users. A request for one user never reaches another user's Elasticsearch account.
Permissions at every level. Your project settings decide what the agent may request, the end user decides what they authorize, and Elasticsearch enforces what its API grants.
Troubleshooting
You pasted the API key into the chat
Create a new key on the API keys page, stop using the old one, and enter the new one only through the secure Add custom connector sheet. Keys typed in a chat stay in its history.
Muse returns unauthorized when it lists the tools
Ask Muse to update the Agent200 connector’s credential and enter the key again in the secure sheet. Say that it goes in the Authorization header with the Bearer prefix.
Muse asks for a local command or a package
Answer that Agent200 is a hosted server over remote streamable HTTP, with API key sign-in. Nothing has to be installed.
Muse does not use Agent200 in a later chat
Start a new chat after connecting, and name Agent200 and Elasticsearch in the request.
Muse shows a Elasticsearch authorization link
You have not connected Elasticsearch yet, or the connection needs to be approved again. Open the link, approve access on Elasticsearch's own page, then ask Muse again.
A tool call is refused or returns less than expected
Agent200 runs only what your project allows. Check that Elasticsearch and the tools you need are enabled in the dashboard's Connectors settings, and that you granted Elasticsearch the access the task needs.
The API key was pasted into a chat or committed
Create a new key on the API keys page, replace it in Muse's MCP settings, and stop using the old one. Paste the key only into Muse's settings, never into a chat.
