Typesense MCP server

What the model can do

Typesense (self-hosted or Typesense Cloud): list collections, their schemas and aliases, search one collection or several, read one document, and, when asked, create, upsert, update, import or delete documents (one, listed ids or by filter), create, change or delete a collection, point or delete an alias, manage synonym, curation and stopword sets, or clear the search cache.

Reads

• typesense_list_collectionsTypesense collections: name, number of documents, created time, default sorting field and the field names and types.
• typesense_get_collectionThe full schema of one Typesense collection: every field with its type and whether it is faceted, optional or sortable.
• typesense_searchSearch one Typesense collection.
• typesense_get_documentOne document from a Typesense collection by its id, cut to 30 fields.
• typesense_multi_searchRun up to 5 Typesense searches in one request (several collections, or one collection several ways); each search's matches come back separately…
• typesense_list_aliasesTypesense aliases: each alias name and the collection it points at.

Acts, when you ask

These change something in Typesense. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

• typesense_create_documentAdd one new document to a Typesense collection.
• typesense_upsert_documentWrite one document to a Typesense collection, REPLACING WHOLE any document with the same id: fields missing from the new copy are deleted and the old…
• typesense_update_documentChange fields of one existing Typesense document.
• typesense_delete_documentPermanently delete one document from a Typesense collection by id.
• typesense_delete_documents_by_filterPermanently delete every document in a Typesense collection that matches filter_by, and report how many went.
• typesense_import_documentsWrite up to 500 documents to a Typesense collection in one import.
• typesense_create_collectionCreate a new, empty Typesense collection with a schema.
• typesense_delete_collectionPermanently DROP a whole Typesense collection: its schema and every document in it.
• typesense_update_collectionChange a Typesense collection's schema: add fields, DROP fields (their values are removed from every document's index and cannot be searched…
• typesense_update_documentsSet the same fields on up to 100 listed Typesense documents (by id, never by a filter): the given fields OVERWRITE their old values…
• typesense_upsert_aliasCreate an alias pointing at a Typesense collection, or REPOINT an existing alias to another collection.
• typesense_delete_aliasDelete a Typesense alias.
• typesense_upsert_synonym_setCreate a Typesense synonym set, or REPLACE an existing one whole (items not given are removed).
• typesense_upsert_synonymCreate or replace one synonym rule in a Typesense synonym set (multi-way, or one-way with a root).
• typesense_delete_synonymDelete one synonym rule from a Typesense synonym set.
• typesense_delete_synonym_setPermanently delete a whole Typesense synonym set with every rule in it; collections linked to it lose those synonyms.
• typesense_upsert_curation_setCreate a Typesense curation set, or REPLACE an existing one whole (curations not given are removed).
• typesense_upsert_curationCreate or replace one curation in a Typesense curation set: for searches matching the rule (a query, exact or contains; a filter; or tags)…
• typesense_delete_curationDelete one curation from a Typesense curation set; matching searches go back to their natural ranking.
• typesense_delete_curation_setPermanently delete a whole Typesense curation set with every curation in it; linked collections lose those pins and hides.
• typesense_upsert_stopwordsCreate or REPLACE a Typesense stopwords set (words ignored in queries that name the set with the stopwords parameter).
• typesense_clear_cacheClear the Typesense node's search result cache (results cached for searches sent with use_cache).

Connect it

First connect Typesense on Dashboard → Connections, then add Memtro to your client once. The Typesense tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Typesense connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

• › What does a search for wireless charger return in products?
• › Which fields in the products collection are facets?
• › How many documents are in the help-articles collection?
• › Point the products alias at products_v2
• › Delete every document in products where discontinued is true

Questions

Is this an official Typesense MCP server?

No. It is Memtro's MCP server with Memtro's Typesense connector behind it: the connector reads Typesense through its API with the credentials you connect on Dashboard → Connections, and Typesense publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

What does it cost?

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in Typesense?

Only when you ask, and only what it has been granted: create a document in a collection; upsert a document, replacing whole any document with the same id; update fields of one document; delete one document; delete the documents in a collection that match a filter; import documents in bulk (create, update, upsert or emplace); create a collection; delete a collection with all its documents; change a collection's schema: add or drop fields, link synonym or curation sets; update the same fields on up to 100 listed documents; create or repoint an alias to a collection; delete an alias; create or replace a synonym set, or one synonym in it; delete a synonym set or one synonym; create or replace a curation set, or one curation (pin or hide results for a query); delete a curation set or one curation; create or replace a stopwords set; clear the search result cache. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.

Which clients work?

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

Other MCP servers · Databases and warehouses

• Postgres MCP server
• MySQL and MariaDB MCP server
• SQL Server MCP server
• BigQuery MCP server
• Snowflake MCP server
• AWS Athena MCP server