vector-mcp-operations

vector-mcp-operations is a skill for Claude Code, Codex from Knuckles-Team/vector-mcp. It costs 48 tokens per session (483 once invoked), scanned A, original, MIT.

A controlled operations guide for vector-mcp, a service that stores document representations for similarity search. It covers document ingestion, retrieval, collection management, system readiness, and troubleshooting.

In plain words
What is it for?
Use it to ingest approved documents, run exact or meaning-based searches, manage collections, check backend readiness, and verify results.
Why use it?
It helps perform search and storage operations safely while enforcing checks around permissions, file locations, sensitive data, and deletion.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/knuckles-team/vector-mcp/vector-mcp-operations
Any agent
npx skills add Knuckles-Team/vector-mcp --skill vector-mcp-operations
Clone the repo
git clone --depth 1 https://github.com/Knuckles-Team/vector-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for vector-mcp-operations

README.md
[![agentmods](https://agentmods.dev/badge/skills/knuckles-team/vector-mcp/vector-mcp-operations.svg)](https://agentmods.dev/skills/knuckles-team/vector-mcp/vector-mcp-operations)
Your own site
<a href="https://agentmods.dev/skills/knuckles-team/vector-mcp/vector-mcp-operations"><img src="https://agentmods.dev/badge/skills/knuckles-team/vector-mcp/vector-mcp-operations.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 483 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00048 $0.00483
Opus 5 $0.00024 $0.00242
Sonnet 5 $0.00010 $0.00097
Haiku 4.5 $0.00005 $0.00048

Measured 5d ago against content hash 92f0d75d4b48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vector-mcp-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 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.

vector_mcp/skills/vector-mcp-operations/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vector MCP Operations

Use the provider's governed MCP tools through GraphOS delegation.

Workflow

  1. Establish the verified GraphSession, tenant, and ACL scope.
  2. Discover the installed action-routed tool schema. Do not infer stale actions or parameters.
  3. Use epistemic_graph unless the operator has selected and configured another currently available backend. Connection details and credentials are never tool arguments.
  4. Inspect before changing. Fence approved mutations as idempotent WorkItems and require explicit confirmation for deletion or overwrite.
  5. For file ingestion, accept only relative names beneath the configured document root. Inline content must have an approved data contract and retention policy.
  6. Select semantic search for conceptual similarity, lexical search for exact terms, and hybrid search when both signals matter. Keep result counts and fusion parameters bounded.
  7. Verify the durable result and report only sanitized status, counts, and opaque references.

Safety contract

  • Persist only policy-approved, PII-sanitized document content. Never persist credentials, endpoints, raw personal identifiers, hostnames, or local paths.
  • Require the verified ambient GraphSession: kg:read for search, kg:write for ingestion, and kg:admin for collection lifecycle/inventory. Collection storage is partitioned by an opaque tenant digest.
  • Resolve credentials through supported runtime secret references and TLS through the shared AgentConfig transport profile. Never bypass verification.
  • Treat unknown ACL, tenant, schema, or tool-contract state as a hard failure.
  • Require explicit approval for destructive, externally visible, or irreversible actions.
  • Keep runtime traces metadata-only, policy-scoped, and privacy-sanitized.
  • Reject absolute document paths, endpoint or credential tool arguments, and uncertified connector activation.

Specialized workflows

Read the workflow catalog only when the request needs a provider-specific procedure, parameter map, script, or reference asset.

Read the full file on GitHub · 52 lines

Files

What ships with it

2 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.

Changes

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.

  1. 5d ago First seen · 52 lines · 48 tokens per session scan A 92f0d75d4b48

Subscribe to this mod's changes

vector-mcp-operations is a skill published in the GitHub repository Knuckles-Team/vector-mcp (15 stars, last pushed 7d ago), licensed MIT. It adds 48 tokens to every session and 483 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

vector-databases

Vector database operations — embed, store, search, and build RAG pipelines.

furkangonel/cowrangler · 21 tokens

orchardcore-ai-documents-elasticsearch

Skill for indexing CrestApps Orchard Core AI Documents with Elasticsearch. Covers Elasticsearch index profiles, dense vector chunk mappings, k-nearest-neighbor retrieval, default search fields, and scoped RAG results. Use this skill when requests mention AI Documents Elasticsearch…

CrestApps/CrestApps.AgentSkills · 131 tokens

crestapps-core-elasticsearch

Skill for integrating Elasticsearch indexing data sources documents vector retrieval and memory in CrestApps.Core.

CrestApps/CrestApps.AgentSkills · 23 tokens

crestapps-core-postgresql

Skill for integrating PostgreSQL pgvector indexing data sources documents vector retrieval and memory in CrestApps.Core.

CrestApps/CrestApps.AgentSkills · 26 tokens

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.

LuuOW/meridian-mcp · 71 tokens

chromadb

Semantic search for model descriptions and content using ChromaDB vector database. Use when searching for similar models, finding related content, querying vector collections, or looking up models by description or semantic similarity.

ssube/conclave · 42 tokens