Integration

Vearch integration

Vearch is a self-hosted distributed vector database. This integration covers the router HTTP API: create, list, inspect and delete databases, create, list, inspect and delete spaces with their vector and scalar field schemas and index parameters, upsert documents, delete documents by id or filter, run approximate nearest-neighbour vector search with filters and field selection, query documents by id or filter, and read cluster health, cluster statistics, server members and partition placement. Alias, user, role, index-maintenance and backup routes are not included. Every response carries the same envelope: a result code, a message and a data payload. The host is part of the credential because every Vearch install is its own deployment; the router listens on port 9001 by default. Authentication is the HTTP basic user name and password the router enforces.

Connect Vearch How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Vearch.Built from the 16 Vearch tools below, on the connection you add once.

Common Vearch use cases

removing documents that are no longer indexed
clearing the rows a filter matches

What you can do with Vearch

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Db, 4 operations

create_databaseCreate databasePOSTCreate a new database.
delete_databaseDelete databaseDELETEDelete a specific database.
get_databaseGet databaseGETGet database.
list_databasesList databasesGETList database.

Space, 4 operations

create_spaceCreate spacePOSTCreate a new space.
delete_spaceDelete spaceDELETEDelete a specific space.
get_spaceGet spaceGETGet a specific space.
list_spacesList spacesGETList vearch space.

Document, 1 operation

delete_documentsDelete documentsPOSTDeletes documents from a Vearch space, addressed by id or selected by filter.

Health, 1 operation

get_cluster_healthGet cluster healthGETShow cluster health.

Partition, 1 operation

list_partitionsList partitionsGETList partitions.

Query, 1 operation

query_documentsQuery documentsPOSTQuery for documents using doc ID and filter parameters.

Search, 1 operation

search_documentsSearch documentsPOSTSearch for documents using vector and filter parameters.

Server, 1 operation

list_serversList serversGETList cluster server.

Stat, 1 operation

get_cluster_statsGet cluster statsGETShow cluster status.

Upsert, 1 operation

upsert_documentsUpsert documentsPOSTUpsert document into database.

Use Vearch from Claude Code, Cursor or Codex

Connect Vearch in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Vearch operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Vearch

Create your workspace
Sign up free. Nothing to install.
Connect Vearch once
Add your Vearch connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Vearch integration FAQ

What can you do with the Vearch integration?

LiveContext exposes 16 operations on Vearch, covering db, space, document and health. Common uses include removing documents that are no longer indexed and clearing the rows a filter matches.