Free cloud databases over MCP: query, store, list and annotate across 15 engines.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
A reference for connecting any MCP client to
a free cloud database. Fifteen engines, one endpoint shape, four tools per
connection β with every engine's version and dialect, every client's config file and its exact key
names, and a troubleshooting section built from the mistakes those key names cause. For a
task-oriented walkthrough, the companion repo mcp-database-server-free is organised by job.
Jump to: engines Β· access model Β· tools Β· client setup Β· troubleshooting Β· picking an engine Β· examples
| Engine | Version | Dialect | CLI it speaks | Port | Access |
|---|---|---|---|---|---|
| PostgreSQL | 16.2 | SQL | psql | 5432 | Native TCP + HTTP + MCP |
| MySQL | 8.0.36 | SQL | mysql | 3306 | HTTP + MCP |
| MongoDB | 7.0.4 | Document / NoSQL | mongosh | 27017 | Native TCP + HTTP + MCP |
| Redis | 7.2.3 | Key-Value / In-Memory | redis-cli | 6379 | Native TCP + HTTP + MCP |
| SQLite | 3.45.1 | SQL | sqlite3 | β | HTTP + MCP |
| Apache Cassandra | 4.1.4 | Wide-Column / CQL | cqlsh | 9042 | HTTP + MCP |
| DynamoDB | 2024.1 | Key-Value / Document | aws CLI | β | HTTP + MCP |
| ClickHouse | 24.1.5 | Columnar / OLAP SQL | clickhouse-client | 9000 | HTTP + MCP |
| Elasticsearch | 8.12.0 | Search / Query DSL | curl / ES client | 9200 | HTTP + MCP |
| Neo4j | 5.17.0 | Graph / Cypher | cypher-shell | 7687 | HTTP + MCP |
| MariaDB | 11.3.2 | SQL | mysql | 3306 | HTTP + MCP |
| InfluxDB | 2.7.4 | Flux / InfluxQL | influx | 8086 | HTTP + MCP |
| Prometheus | 2.50.1 | PromQL | promtool / curl | 9090 | HTTP + MCP |
| TimescaleDB | 2.14.2 | SQL (PostgreSQL + Timescale) | psql | 5432 | HTTP + MCP |
| CockroachDB | 23.2.4 | SQL (PostgreSQL-compatible) | cockroach sql / psql | 26257 | HTTP + MCP |
Port is the port that engine's protocol conventionally uses β it tells you which dialect and
client tooling apply, not that a socket is listening. Each engine has a page at
https://freebase.cloud/free-<slug>-cloud-instance (slugs: postgresql, mysql, mongodb,
redis, sqlite, cassandra, dynamodb, clickhouse, elasticsearch, neo4j, mariadb,
influxdb, prometheus, timescaledb, cockroachdb), plus a Claude guide at
https://freebase.cloud/how-to-connect-claude-to-<slug> β for example
the Elasticsearch instance page.
Two distinct paths. Confusing them is the source of most setup trouble.
Native wire protocol β three engines. PostgreSQL, Redis and MongoDB accept real drivers over
their real protocols: psql/libpq/Prisma/SQLAlchemy/pgx, redis-cli/ioredis/redis-py/Lettuce over
RESP2, mongosh/Mongoose/the native driver over OP_MSG. Nothing is proxied or reshaped.
HTTP and MCP β all fifteen. The other twelve are reached through the hosted HTTP query API and through MCP. They speak their own dialects β CQL to Cassandra, Cypher to Neo4j, Flux to InfluxDB β but the transport is HTTP, not a raw socket. If you are wiring up an AI assistant this is the path you want regardless of engine, because it is identical for all of them:
The token sits in the URL path, so no Authorization header appears anywhere in this document.
The consequence: the URL is the credential. Don't commit it, don't paste it into a shared config,
and rotate it from Settings β MCP if you do either. Transport is Streamable HTTP, which
uses server-sent events internally for streamed responses β not the same thing as the deprecated
HTTP+SSE transport with its separate /sse endpoint and POST /messages. Clients offering both:
choose streamable.
Four tools per connection, prefixed with the connection name you chose, not the engine name.
A connection called db gives you:
| Tool | Purpose | What it means per engine |
|---|---|---|
db_query | Read, in the engine's native language | SQL Β· CQL Β· Cypher Β· Flux Β· PromQL Β· ES query DSL Β· Mongo find/aggregate Β· Redis commands |
db_store | Insert, upsert, write | INSERT Β· MERGE Β· _bulk Β· line protocol Β· SET Β· PutItem |
db_list_tables | Enumerate containers | tables Β· collections Β· keyspaces Β· indices Β· measurements Β· metric names Β· keys |
db_annotate_table | Attach a human description to a container | so the model knows what the columns mean |
Two engines add helpers: PostgreSQL gets pg_dump, pg_restore and pg_tables; SQLite gets sqlite_master and sqlite_version.
Use annotate_table. Highest-return five minutes in this document. A model that can list your
tables still has to guess whether status holds 'active' or 1, whether amount_cents is cents
or dollars, and whether deleted_at IS NULL is how you filter. One paragraph per table, written
once, persists on the connection and applies to every conversation in every client using that token.
Sign up on the freebase.cloud dashboard (no card), create a session, pick an engine, then Settings β MCP β New Token β select the connection β copy the URL. Confirm it works before configuring any client β four tool names printed means anything still broken is configuration:
| Client | Config location | Top-level key | URL key | type value |
|---|---|---|---|---|
| Claude Desktop / web / Cowork | UI only | β | β | β |
| Claude Code | .mcp.json / user config | mcpServers | url | "http" (required) |
| ChatGPT | UI (developer mode) | β | β | β |
| OpenAI Responses API | request body | tools[] | server_url | "mcp" |
| Cursor | ~/.cursor/mcp.json or .cursor/mcp.json | mcpServers | url | omit entirely |
| Windsurf | ~/.codeium/windsurf/mcp_config.json | mcpServers | serverUrl | β |
| VS Code / Copilot Chat | .vscode/mcp.json | servers | url | "http" |
| Zed | settings.json | context_servers | url | β |
| Cline | MCP settings JSON | mcpServers | url | "streamableHttp" |
| Roo Code | .roo/mcp.json | mcpServers | url | "streamable-http" |
| Gemini CLI | settings.json | mcpServers | httpUrl | β |
| Warp | Settings β AI β Manage MCP servers | (none) | url | β |
| n8n | MCP Client Tool node | β | Endpoint field | HTTP Streamable |
| LangChain / LlamaIndex | Python | β | url | "http" |
UI only. Settings (β, / Ctrl+,) β Connectors (Customize β Connectors in newer builds) β
Add custom connector β paste the URL β Add. Enable per conversation with the + button in
the composer. Available on Free, Pro, Max, Team and Enterprise; Free accounts get one custom
connector. claude_desktop_config.json has no representation for a remote HTTP MCP server β a
post telling you to add one there predates streamable HTTP. The engine-specific version of these
steps lives at
how to connect Claude to PostgreSQL
and its siblings for the other slugs.
streamable-http is accepted as an alias for http.
Settings β Apps β Advanced settings β enable developer mode β Apps β Create β paste the endpoint β Auth None β Scan Tools β Create. Also check Settings β Connectors; OpenAI's two docs pages disagree about where this lives. Developer mode is documented for Pro, Plus, Business, Enterprise and Edu; full write access is currently rolling out to Business, Enterprise and Edu workspaces, so on some plans you get read-only tool access today.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/freebase-cloud)<a href="https://allmcps.com/mcp/freebase-cloud"><img src="https://allmcps.com/api/badge/freebase-cloud?style=directory" alt="Freebase.cloud on AllMCPs" /></a>