Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add celticht32/Couchbase-Skills-for-Claude.ai --skill couchbase-mcpgit clone --depth 1 https://github.com/celticht32/Couchbase-Skills-for-Claude.aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-mcp)<a href="https://agentmods.dev/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-mcp"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-mcp"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00240 | $0.03498 |
| Opus 5 | $0.00120 | $0.01749 |
| Sonnet 5 | $0.00048 | $0.00700 |
| Haiku 4.5 | $0.00024 | $0.00350 |
Grade A, and why
couchbase-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Couchbase MCP
A skill for operating Couchbase through an MCP server. Two servers cover this space, and they are not interchangeable — pick based on how much of the surface you need.
Which MCP server — read this first
| celticht32/MCP-Couchbase (this skill's primary) | Couchbase-Ecosystem/mcp-server-couchbase (official) | |
|---|---|---|
| Maintainer | Independent (Chris Ahrendt / celticht32) | Couchbase-Ecosystem — community-maintained; NOT covered by Couchbase's support team unless licensed (see below) |
| Surface | ~167 tools: full data plane plus cluster admin (buckets/scopes/collections, users/RBAC, rebalance/failover/recovery, XDCR, eventing, backup, KMIP/DARE), 8.x features (vector indexes, synonyms, user lock), Capella v4 control plane, perf diagnostics | Deliberately narrow: bucket-scoped data plane only — Cluster Health, Data/Schema, Key-Value, Query, Performance (index list, Index Advisor, slow-query analysis) |
| Admin ops (create bucket, rebalance, failover, XDCR, eventing, backup, encryption) | Yes | No — not in scope |
| Capella control plane (orgs/projects/clusters/allowlists) | Yes (read-only capella_* tools) |
No |
| Auth / runtime | Cluster creds + Capella API key; two server processes | Python 3.10+, PyPI/Docker; CB_CONNECTION_STRING + basic auth or mTLS; STDIO or Streamable HTTP; bucket-scoped |
| Safety | CB_MCP_READ_ONLY_MODE + per-tool confirm:true gate |
CB_MCP_READ_ONLY_MODE / CB_MCP_READ_ONLY_QUERY_MODE (read-only query default) |
| Enterprise support | None (independent project) | Available by licensing Couchbase AI Data Plane, which also entitles Couchbase Agent Memory + Agent Catalog (GA 2026-06-30) |
How to choose:
- Cluster administration, XDCR, eventing, backup, encryption, Capella control-plane inspection, or perf-analysis beyond Index Advisor → celticht32/MCP-Couchbase. The official server can't do these.
- Just KV + SQL++ + schema/health/Index-Advisor on a single bucket, want the vendor-tracked package, or need enterprise support via an AI Data Plane license → the official Couchbase-Ecosystem server.
- Tool names below (
cb_*,admin_*,capella_*) are the celticht32 server's. The official server uses its own (shorter) tool names — check its README when connected to it. The two do not share a namespace.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/capella-v4.md 7.0 KB
- references/cluster-admin.md 8.9 KB
- references/couchbase-8x.md 7.0 KB
- references/data-plane.md 6.5 KB
- references/diagnostics.md 6.6 KB
- references/observability.md 9.3 KB
- references/operational-runbooks.md 12 KB
- references/safety.md 7.9 KB
- references/security-best-practices.md 12 KB
- references/tool-index.md 7.5 KB
- references/troubleshooting.md 9.7 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 171 lines · 240 tokens per session scan A 6aa49c2e4a78
couchbase-mcp is a skill published in the GitHub repository celticht32/Couchbase-Skills-for-Claude.ai (4 stars, last pushed 2mo ago), licensed MIT. It adds 240 tokens to every session and 3,498 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
db-seed
Generate database seed scripts with realistic sample data. Reads Drizzle schemas or SQL migrations, respects foreign key ordering, produces idempotent TypeScript or SQL seed files. Handles D1 batch limits, unique constraints, and domain-appropriate data. Use when populating dev/demo/test databases. Triggers: 'seed…
d1-drizzle-schema
Generate Drizzle ORM schemas for Cloudflare D1 databases with correct D1-specific patterns. Produces schema files, migration commands, type exports, and DATABASESCHEMA.md documentation. Handles D1 quirks: foreign keys always enforced, no native BOOLEAN/DATETIME types, 100 bound parameter limit, JSON stored as TEXT.…
d1-migration
Cloudflare D1 migration workflow: generate with Drizzle, inspect SQL for gotchas, apply to local and remote, fix stuck migrations, handle partial failures. Use when running migrations, fixing migration errors, or setting up D1 schemas.
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.