Redis MCP vs MCP Clickhouse
A side-by-side look at the Redis MCP and MCP Clickhouse MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Redis MCP for databases work as a local process; choose MCP Clickhouse for databases as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Redis MCP when
- You need dedicated capabilities in the Databases domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
UPSTASH_REDIS_REST_URL, UPSTASH_REDIS_REST_TOKEN, UPSTASH_REDIS_TCP_URL, REDIS_URL. - You want tools like
redis_run_commands, redis_search_docs.
Choose MCP Clickhouse when
- You need dedicated capabilities in the Databases domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: other.
- You want tools like
list_databases, list_tables, run_query.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Databases | Databases |
| Quality signal | 55/100 · Good | 67/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | other |
| Pricing | Not declared | Free |
| Required env vars | UPSTASH_REDIS_REST_URLUPSTASH_REDIS_REST_TOKENUPSTASH_REDIS_TCP_URLREDIS_URL | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 890 |
| Directory activity | 2 views 0 installs 0 upvotes | 6 views 0 installs 0 upvotes |
| Tools | 2 | 3 |
| Full listing | View Redis MCP | View MCP Clickhouse |
Tools & capabilities
Redis MCP tools 2
redis_run_commandsRun one or more Redis commands against an Upstash Redis database (this server is ONLY for Upstash Redis). Commands are sent over HTTP/REST or native TCP depending on how the target database is configured — you don't choose the transport. By default multiple commands run as a pipeline: each returns its own result/error, and one failure does not abort the others. Set transaction:true to run them atomically (MULTI/EXEC). For discovery prefer SCAN over KEYS, and use TYPE to inspect a key. A valid command that fails (e.g. WRONGTYPE) returns a per-command error while the rest of the pipeline still runs; a malformed/unknown command can cause the whole request to be rejected. Upstash Redis Search runs through THIS tool via SEARCH.* commands (SEARCH.LISTINDEXES/CREATE/QUERY/AGGREGATE/COUNT/DESCRIBE) — NOT RediSearch's FT.*; filters/aggregations are JSON strings. If you don't know the index name, run SEARCH.LISTINDEXES first; then SEARCH.DESCRIBE <index> for field names/types, and call redis_search_docs for syntax. Three gotchas: (1) a filter applies to ALL indexed documents unless you scope it, e.g. {"type":"story"} — an empty {} counts every type; (2) a plain text value like {"title":"x"} does fuzzy/smart matching, so for an exact word or adjacent phrase use {"title":{"$phrase":"x"}}; (3) add SELECT <n> field... to a query to return only the fields you need instead of whole documents.redis_search_docsLook up **Upstash Redis** documentation — any command, feature, option, or syntax. Covers the whole Upstash Redis surface: core Redis commands, the REST API, pipelines/transactions, and Upstash-specific features. This INCLUDES Upstash Redis Search — the SEARCH.* full-text family (SEARCH.CREATE / SEARCH.QUERY / SEARCH.AGGREGATE / SEARCH.COUNT / ...), whose JSON-based index schema and query syntax are Upstash-specific and DIFFER from Redis Labs' RediSearch FT.*, so they are unlikely to be in your training data — verify them here. Reach for this whenever you're unsure about a command, option, or syntax, and ALWAYS before writing a SEARCH.* command. Pass a natural-language query.
MCP Clickhouse tools 3
list_databasesList available ClickHouse databaseslist_tablesList available ClickHouse tables in a database, including schema, comment, row count, and column count. Integers outside [-9007199254740991, 9007199254740991] in table metadata are returned as decimal strings. Pagination tokens are single-use and retained for up to one hour.run_queryExecute SQL queries in ClickHouse. Queries run in read-only mode by default. Bind optional params by name with {name:Type} placeholders, such as {name:String} or {vector:Array(Float32)}. Values may be JSON scalars, nulls, or arrays. Pass exact large integers as decimal strings. JSON lists and objects cannot bind to Tuple and Map types. Python percent formatting and $name$ raw binary parameters are not supported. Parameter values stay out of the MCP server's normal SQL log lines, but may appear in errors and backend logs. Set CLICKHOUSE_ALLOW_WRITE_ACCESS=true to allow DDL and DML operations. Set CLICKHOUSE_ALLOW_DROP=true to additionally allow destructive operations (DROP, TRUNCATE, DELETE, UPDATE, REPLACE TABLE/PARTITION, CREATE OR REPLACE, CLEAR COLUMN/INDEX/PROJECTION, DETACH PERMANENTLY). That gate is a best-effort accident guard, not a security boundary. Integers outside [-9007199254740991, 9007199254740991] are returned as decimal strings. Two optional checks also run through this tool. Use DESCRIBE (<query>) when you need a query's output columns and types; it inspects the result schema and surfaces analysis errors such as an unknown column, but a query that describes cleanly can still fail at runtime. Consider EXPLAIN ESTIMATE <query> before a SELECT that could be expensive; it returns the estimated parts, rows and marks read from MergeTree family tables, which is not run time and not result size. Neither runs the query body, though analysis can execute scalar subqueries.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Redis MCP
{
"mcpServers": {
"redis-mcp": {
"command": "npx",
"args": [
"-y",
"@upstash/redis-mcp"
],
"env": {
"UPSTASH_REDIS_REST_URL": "YOUR_UPSTASH_REDIS_REST_URL_HERE",
"UPSTASH_REDIS_REST_TOKEN": "YOUR_UPSTASH_REDIS_REST_TOKEN_HERE",
"UPSTASH_REDIS_TCP_URL": "YOUR_UPSTASH_REDIS_TCP_URL_HERE",
"REDIS_URL": "YOUR_REDIS_URL_HERE"
}
}
}
}
MCP Clickhouse
{
"mcpServers": {
"clickhouse-mcp-clickhouse": {
"command": "uvx",
"args": [
"mcp-clickhouse"
]
}
}
}
Frequently asked questions
Redis MCP is categorized under Databases and uses a local stdio subprocess. MCP Clickhouse belongs to Databases and uses a local stdio subprocess. Pick Redis MCP for databases work and MCP Clickhouse for databases.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Redis MCP has no declared pricing — check the project's own site. MCP Clickhouse is listed as free. Auth: other. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add redis-mcp and clickhouse-mcp-clickhouse as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Redis MCP has a quality signal of 55/100 (Good) with 2 views, 0 installs and 0 GitHub stars. MCP Clickhouse has 67/100 (Great) with 6 views, 0 installs and 890 GitHub stars.