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 Knuckles-Team/vector-mcp --skill vector-backend-operationsgit clone --depth 1 https://github.com/Knuckles-Team/vector-mcpWrote 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/knuckles-team/vector-mcp/vector-backend-operations)<a href="https://agentmods.dev/skills/knuckles-team/vector-mcp/vector-backend-operations"><img src="https://agentmods.dev/badge/skills/knuckles-team/vector-mcp/vector-backend-operations/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/knuckles-team/vector-mcp/vector-backend-operations"><img src="https://agentmods.dev/badge/skills/knuckles-team/vector-mcp/vector-backend-operations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00113 | $0.01074 |
| Opus 5.5 | $0.00045 | $0.00430 |
| Sonnet 5.5 | $0.00023 | $0.00215 |
| Haiku 4.5 | $0.00011 | $0.00107 |
Grade A, and why
vector-backend-operations 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 1mo 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vector Backend Operations
Backend selection and connection wiring for the vector-mcp MCP server. Both the
vector_collection_management and vector_search tools take the same db_type +
connection parameters — this skill is the reference for getting those right per
engine.
When to use
- Choose a vector backend for a workload (embedded vs. networked, dev vs. prod).
- Assemble the correct connection parameters for a chosen
db_type. - Migrate a corpus between backends (e.g. local chromadb → hosted qdrant).
- Diagnose "backend unreachable / wrong params" failures before running collection or search calls.
When NOT to use
- Creating/loading/deleting collections →
vector-collection-management. - Semantic / lexical / hybrid retrieval →
vector-hybrid-search.
Prerequisites & environment
Connect via the mcp-client skill against the vector-mcp MCP server. The
relevant backend extra must be installed on the server (vector-mcp[chromadb],
[postgres], [qdrant], [couchbase], [mongodb], or [all]).
Backends & connection parameters
db_type selects the engine; the other params depend on it:
db_type |
Typical params | Notes |
|---|---|---|
chromadb |
db_path (embedded) or host/port |
Zero-infra local default |
postgres |
host, port, db_name, username, password |
pgvector-backed |
qdrant |
host, port |
Fast ANN, fastembed extra |
couchbase |
host, db_name, username, password |
|
mongodb |
host, port, db_name, username, password |
Atlas Vector Search |
The same params flow into vector_collection_management and vector_search, so
once you know the backend shape, reuse it across every call.
Tools & actions
Backend selection is not a standalone action — it is the db_type + connection
arguments shared by both tools:
| Condensed tool | Actions using these params |
|---|---|
vector_collection_management |
create_collection, add_documents, list_collections, delete_collection |
vector_search |
semantic_search, lexical_search, search |
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.
- 1mo ago First seen · 96 lines · 113 tokens per session scan A b3158e94bec1
vector-backend-operations is a skill published in the GitHub repository Knuckles-Team/vector-mcp (15 stars, last pushed yesterday), licensed MIT. It adds 113 tokens to every session and 1,074 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
mongodb-mcp-v3-migration
Migrates external consumer code from the mongodb-mcp-server v1/v2 single-package API to the v3 scoped-package structure. In v3, mongodb-mcp-server is a binary-only package (npx / MCPB); library embedding uses @mongodb-js/mcp-cli, @mongodb-js/mcp-core, @mongodb-js/mcp-http-runners, @mongodb-js/mcp-tools-, and the other…
crestapps-core-postgresql
Skill for integrating PostgreSQL pgvector indexing data sources documents vector retrieval and memory in CrestApps.Core.
astra-vector-backend
Design Astra DB Data API and vector-search backends for retrieval, metadata filtering, and LangChain-compatible stores.
vector-databases
Vector database operations — embed, store, search, and build RAG pipelines.
vector-databases
Vector database engineering covering Pinecone, Weaviate, Chroma, Qdrant, pgvector, and FAISS — including embedding pipeline design, HNSW index parameter tuning, hybrid dense+sparse (BM25) search, metadata filtering, namespace and tenant sharding, and RAG retrieval patterns for production knowledge systems.
vector-store
Vector store authority — Qdrant operations, collection management, embedding submission, filtered semantic search, index optimization, payload indexing, and multi-tenant isolation patterns.