Integration

ZincSearch integration

ZincSearch is a self-hosted full-text search engine that serves its own JSON API and an Elasticsearch-compatible API on the same port. This integration covers both: create, list, inspect and delete indexes, read and set their mappings and settings, refresh an index, index, read, update and delete documents one at a time, ingest a batch through the JSON bulk route, search an index with the native search body or with the Elasticsearch query DSL, delete documents by query, analyse text with an ad-hoc analyser or with an index analyser, create, list, read, update and delete index templates, add and remove Elasticsearch aliases and read them, manage users and roles and list the available permissions, and read server health and version. The host is part of the credential because every ZincSearch install is its own deployment; it listens on port 4080 by default. Authentication is the HTTP basic user name and password of a ZincSearch account.

Connect ZincSearch How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in ZincSearch.Built from the 40 ZincSearch tools below, on the connection you add once.

What you can do with ZincSearch

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.

Index template, 5 operations

create_index_templateCreate index templatePOSTCreate update index template.
delete_index_templateDelete index templateDELETEDelete template.
get_index_templateGet index templateGETGet index template.
list_index_templatesList index templatesGETList index teplates.
update_index_templateUpdate index templatePUTCreate update index template.

Doc, 4 operations

create_documentCreate documentPOSTCreate or update document.
delete_documentDelete documentDELETEDelete document.
get_documentGet documentGETget document with id.
index_documentIndex documentPUTCreate or update document with id.

Index, 4 operations

create_indexCreate indexPOSTCreate index.
delete_indexDelete indexDELETEDelete index.
get_indexGet indexGETGet index metadata.
list_indexesList indexesGETList indexes.

User, 4 operations

create_userCreate userPOSTCreate user.
delete_userDelete userDELETEDelete user.
list_usersList usersGETList user.
update_userUpdate userPUTUpdate user.

Mapping, 3 operations

get_index_mappingGet index mappingGETGet index mappings.
get_index_mapping_elasticsearchGet index mapping elasticsearchGETGet index mappings for compatible ES.
set_index_mappingSet index mappingPUTSet index mappings.

Role, 3 operations

create_roleCreate rolePOSTCreate role.
delete_roleDelete roleDELETEDelete role.
list_rolesList rolesGETList role.

Analyze, 2 operations

analyze_textAnalyze textPOSTAnalyze.
analyze_text_with_indexAnalyze text with indexPOSTAnalyze.

Search, 2 operations

search_indexSearch indexPOSTSearch V1.
search_index_with_query_dslSearch index with query dslPOSTSearch V2 DSL for compatible ES.

Setting, 2 operations

get_index_settingsGet index settingsGETGet index settings.
set_index_settingsSet index settingsPUTSet index Settings.

Alia, 1 operation

get_index_aliasesGet index aliasesGETGet index alias for compatible ES.

Aliase, 1 operation

update_aliasesUpdate aliasesPOSTAdd or remove index alias for compatible ES.

Bulkv2, 1 operation

bulk_index_documentsBulk index documentsPOSTBulkv2 documents.

Delete by query, 1 operation

delete_documents_by_queryDelete documents by queryPOSTSearches the index and deletes all matched documents.

E, 1 operation

create_index_elasticsearchCreate index elasticsearchPUTCreate index for compatible ES.

Healthz, 1 operation

get_healthGet healthGETGet healthz.

Index name, 1 operation

list_index_namesList index namesGETList index Name.

Permission, 1 operation

list_permissionsList permissionsGETList permissions.

Refresh, 1 operation

refresh_indexRefresh indexPOSTResfresh index.

Update, 1 operation

update_documentUpdate documentPOSTUpdate document with id.

Version, 1 operation

get_versionGet versionGETGet version.

Use ZincSearch from Claude Code, Cursor or Codex

Connect ZincSearch in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its ZincSearch 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 ZincSearch

Create your workspace
Sign up free. Nothing to install.
Connect ZincSearch once
Add your ZincSearch 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.