nlqdb — analytical memory for AI agents

Install

Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/nlqdb-com-nlqdb

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

3 read · 1 write · 2 delete · 1 not yet classified

Secrets

None asked for

Install scripts

Nothing to install (hosted)

Runs as

Hosted (remote endpoint)

Tools (7)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• nlqdb_connect_databaseConnect an existing database so the agent can query it in English

  Connect an existing ClickHouse or Postgres database so the agent can query it in natural language with nlqdb_query — no migration, no schema upload. Pass the engine and a connection URL; the credential is stored sealed server-side and never echoed back. Returns the new dbId and a preview of the discovered schema.

• nlqdb_describeDescribe one memory databaseread-only

  Inspect the shape of one of your agent's memory databases. Return schema metadata (slug, engine, schema name) for one database. Requires a user-scoped key (sk_live_ or sk_mcp_).

• nlqdb_insertInsert rows; unseen tables and fields are createdcan change or delete data

  Insert structured rows into a table with no data modelling: an unseen table or field is created in the same transaction, typed from the values, and the rows land exactly as sent — no model call. Pass `key` to upsert: a row whose key exists is updated instead of duplicated. Returns the stored rows (generated ids included) and, when the schema widened, the DDL it ran. Use it whenever you hold the exact values; use nlqdb_query to write something described in words.

• nlqdb_list_databasesList your agent's memory databasesread-only

  List the memory databases your agent can query, scoped to the authenticated user. Requires a user-scoped key (sk_live_ or sk_mcp_). Returns engine per row.

• nlqdb_queryQuery your agent's memory in natural languagecan change or delete data

  Query your agent's structured memory in natural language — a real database it can GROUP BY / JOIN / aggregate over, not just recall. Returns rows + the compiled SQL (in trace). The database is materialised on first reference — no separate create tool. Destructive plans return requires_confirm: true + a diff; re-call with confirm: true to commit.

• nlqdb_readRead your agent's memory in natural language (never writes)read-only

  Read-only natural-language query over your agent's memory — SELECT / aggregate / JOIN over existing data. Guaranteed never to write, create, or modify: a request whose plan would change data is refused (use nlqdb_query for that), so this tool is safe to mark 'always allow' in your host. Auto-targets your only database; pass `db` to pick one when you have several. Returns rows + the compiled SQL in trace.

• nlqdb_rememberRemember something in your agent's memory

  Write a typed row into your agent's memory database — a fact to recall later, a conversation episode, or an entity (person/project/thing). Materialises directly into the agent_memory_v1 schema with no LLM in the loop, so it's deterministic. Omit `db` on first use and this tool will find (or provision) the agent_memory_v1 database for you and echo `dbId` (and `db_created: true` on a fresh provision) in the result — pin that id on subsequent calls. Query it back later with nlqdb_query (which can GROUP BY / aggregate over what you remembered). Set kind + tags on facts — they are the columns those…

Signals

Stars

2

Forks

2

Open issues

0

Last commit

Oct 24, 2026 (5 days ago)

Last release

Oct 22, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name

com.nlqdb/nlqdb

Version

0.1.1

Auth

Auth not stated

License

License unknown

Repository

github.com/nlqdb/nlqdb

Website

nlqdb.com/agents/?utm_source=mcp-registry

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql