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 agentmods add skills/knuckles-team/vector-mcp/vector-collection-managementnpx skills add Knuckles-Team/vector-mcp --skill vector-collection-managementgit 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-collection-management)<a href="https://agentmods.dev/skills/knuckles-team/vector-mcp/vector-collection-management"><img src="https://agentmods.dev/badge/skills/knuckles-team/vector-mcp/vector-collection-management.svg" alt="Measured on agentmods" 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 | $0.00123 | $0.01058 |
| Opus 5 | $0.00062 | $0.00529 |
| Sonnet 5 | $0.00025 | $0.00212 |
| Haiku 4.5 | $0.00012 | $0.00106 |
Grade A, and why
vector-collection-management 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 5d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vector Collection Management
Lifecycle operations on vector-store collections — the named indexes that hold
embedded document chunks — via the vector-mcp MCP server. One condensed,
action-routed tool covers create / add / list / delete so the same call shape works
across every backend.
When to use
- Create (or get-or-create) a collection to hold a corpus for RAG.
- Ingest documents into a collection — from a
document_directory, a list ofdocument_paths(files/URLs), or inlinedocument_contentsstrings. - List the collections that exist on a backend.
- Delete a collection you no longer need.
When NOT to use
- Querying / retrieving from a collection →
vector-hybrid-search. - Picking a backend, wiring host/port/credentials, or comparing engines →
vector-backend-operations. - Persisting derived knowledge into the epistemic-graph KG → this is a vector backend, not a KG source; use the graph-os tools for KG writes.
Prerequisites & environment
Connect via the mcp-client skill against the vector-mcp MCP server. Every
action takes the connection parameters inline (or falls back to server defaults):
| Parameter | Notes |
|---|---|
db_type |
Backend: chromadb, postgres, qdrant, couchbase, mongodb |
db_path |
On-disk path (e.g. for embedded chromadb) |
host / port |
Networked backends |
db_name / username / password |
Auth for postgres / couchbase / mongodb |
collection_name |
Target collection (defaults to memory in the retriever) |
Embedding is handled server-side by the configured embedding model
(agent-utilities[embeddings-openai] or HuggingFace/sentence-transformers extras).
Tools & actions
| Condensed tool | Actions |
|---|---|
vector_collection_management |
create_collection, add_documents, delete_collection, list_collections |
Key parameters
overwrite— oncreate_collection, replace an existing collection instead of get-or-create.document_directory/document_paths/document_contents— the three mutually-usable ingestion inputs forcreate_collectionandadd_documents.confirm— required guard ondelete_collection.
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.
- 5d ago First seen · 98 lines · 123 tokens per session scan A 0de42dabdc2e
vector-collection-management is a skill published in the GitHub repository Knuckles-Team/vector-mcp (15 stars, last pushed 7d ago), licensed MIT. It adds 123 tokens to every session and 1,058 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
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.
qdrant-clients-sdk
Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.
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…
qdrant-hybrid-search-prefetches
Constructing prefetch queries for hybrid retrieval, including sparse/dense and multi-field setups, and choosing a sparse embedding model. Use when someone asks 'dense and sparse in one search?', 'how to combine multiple fields for retrieval?', 'payloads or sparse vectors for lexical?', 'which sparse embedding model to…
qdrant-model-migration
Guides embedding model migration in Qdrant without downtime. Use when someone asks 'how to switch embedding models', 'how to migrate vectors', 'how to update to a new model', 'zero-downtime model change', 'how to re-embed my data', or 'can I use two models at once'. Also use when upgrading model dimensions, switching…