Chroma’s official MCP server: vector search and collection management for RAG workflows.
Nothing to run from here
Couchbase is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
100/100
trust score
20
downloads a day
local
runs on your machine
650
downloads in 30d
What it does
Couchbase MCP Server - Enable AI agents to connect to and interact with Couchbase clusters.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user couchbase-mcp '--' uvx couchbase-mcp-server
# 2 — ask your agent for something these tools do
# tool_obj
Couchbase costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
COAll 1 server
couchbase1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Couchbase as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user couchbase-mcp '--' uvx couchbase-mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take CB_CONNECTION_STRING (Couchbase connection string. Required for connecting to the cluster.), CB_USERNAME (Couchbase database username. Required for basic authentication.), CB_PASSWORD (Couchbase database password. Required for basic authentication.), CB_CA_CERT_PATH (Couchbase CA certificate path. Required for TLS authentication in non Capella clusters.), CB_CLIENT_CERT_PATH (Couchbase client certificate path. Required for mTLS authentication.), CB_CLIENT_KEY_PATH (Couchbase client key path. Required for mTLS authentication.), CB_MCP_READ_ONLY_MODE (Couchbase read only mode. Set to true to allow disable write operations across both KV and query. KV write tools are not loaded and SQL++ queries that modify da), CB_MCP_TRANSPORT (Transport mode for the server (stdio, http or sse). Default is stdio), CB_MCP_HOST (Host to run the MCP server on (default: 127.0.0.1). Used only for HTTP and SSE transport modes.), CB_MCP_PORT (Port to run the MCP server on (default: 8000). Used only for HTTP and SSE transport modes.), CB_MCP_DISABLED_TOOLS (Tools to disable. Accepts comma-separated tool names (e.g., 'tool_1,tool_2') or a file path containing one tool name per line.), CB_MCP_CONFIRMATION_REQUIRED_TOOLS (Comma-separated tool names that require user confirmation before execution. Also accepts a file path containing one tool name per line. Requires the MCP client), CB_MCP_LOG_LEVEL (Logging level for the MCP server. One of off, debug, info, warning, error. Use 'off' to disable logging entirely. Invalid values fall back to info. Default is i), CB_MCP_LOG_SINKS (Comma-separated list of log destinations. Allowed values: stderr, file. Include 'file' to write per-level log files; include 'stderr' to write to the console. D), CB_MCP_LOG_FILE (Base path for the per-level log files. One rotating file is written per level (e.g. mcp_server.info.log, mcp_server.error.log). Only used when 'file' is in CB_M), CB_MCP_LOG_ROTATION_MAX_SIZE_MB (Global maximum size in MB per-level log file before it rotates, inherited by every level unless overridden by a per-level CB_MCP_LOG_<LEVEL>_ROTATION_MAX_SIZE_M), CB_MCP_LOG_MAX_BYTES ([DEPRECATED] Global rotation size in bytes; use CB_MCP_LOG_ROTATION_MAX_SIZE_MB (MB) instead. Still honored for backward compatibility but ignored when CB_MCP_L), CB_MCP_LOG_ERROR_ROTATION_MAX_SIZE_MB (Rotation size in MB for the ERROR log file. Overrides CB_MCP_LOG_ROTATION_MAX_SIZE_MB for ERROR; inherits it when unset. 0 is invalid and falls back to the inhe), CB_MCP_LOG_WARNING_ROTATION_MAX_SIZE_MB (Rotation size in MB for the WARNING log file. Overrides CB_MCP_LOG_ROTATION_MAX_SIZE_MB for WARNING; inherits it when unset. 0 is invalid and falls back to the), CB_MCP_LOG_INFO_ROTATION_MAX_SIZE_MB (Rotation size in MB for the INFO log file. Overrides CB_MCP_LOG_ROTATION_MAX_SIZE_MB for INFO; inherits it when unset. 0 is invalid and falls back to the inheri), CB_MCP_LOG_DEBUG_ROTATION_MAX_SIZE_MB (Rotation size in MB for the DEBUG log file. Overrides CB_MCP_LOG_ROTATION_MAX_SIZE_MB for DEBUG; inherits it when unset. 0 is invalid and falls back to the inhe), CB_MCP_LOG_RETENTION_BACKUP_COUNT (Number of rotated backup files kept per-level log file, excluding the live file. Applies to every level unless overridden per level. Set to 0 to keep only the l), CB_MCP_LOG_ERROR_RETENTION_BACKUP_COUNT (Rotated backups kept for the ERROR log file. Overrides CB_MCP_LOG_RETENTION_BACKUP_COUNT for ERROR; inherits it when unset.), CB_MCP_LOG_WARNING_RETENTION_BACKUP_COUNT (Rotated backups kept for the WARNING log file. Overrides CB_MCP_LOG_RETENTION_BACKUP_COUNT for WARNING; inherits it when unset.) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
1 tool, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Couchbase or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 100 / 100
Release 1.0.1.post1 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score100
Findings2 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digest8b9bbe1dc805ed94114558b57059304c243791fe6e0bc0d13031d733274c7f21
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
The source has registrations with unknown names: the tools registered at src/mcp_server.py:494 get their names only at run time (a loop over a list the code builds, a name it computes), so they are not in this surface and were not analysed. To see them, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest8b9bbe1dc805ed94
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.0.1.post1. Pin a release below and the command asks for exactly that one.
1.0.1.post1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Couchbase can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.