AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Okf Mongodb

skill-xsavikx-okf-skills-okf-mongodb · by xSAVIKx

MongoDB connector that produces and ingests Open Knowledge Format (OKF) bundles by sampling documents to infer each collection's schema. Emits one concept per collection with a Name | Type | Presence table (top-level fields, with mixed types shown as a union and presence as the percentage of sampled documents). The connection URI is bound via the MONGODB_URI environment variable and stripped of c…

↗ Website ↗ Repository
— No reviews yet
0 installs
16 views
0.0% view→install

Install

$ agentstack add skill-xsavikx-okf-skills-okf-mongodb

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Okf Mongodb? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

MongoDB OKF Connector

This skill provides a Go-based CLI tool to document a MongoDB database as an Open Knowledge Format (OKF) bundle. MongoDB is schemaless, so the connector samples documents from each collection and infers a top-level field schema: field name, type (a sorted union when documents disagree), and presence (the percentage of sampled documents that contain the field).

When to Use

Use this skill when you need to:

  1. Catalog a MongoDB database — one MongoDB Collection concept per collection.
  2. Capture an inferred field schema (Name | Type | Presence) as grounding for

enrichment.

  1. Verify a bundle against a live database in CI, optionally creating missing

collections.

MongoDB has no per-field comment store, so enriched descriptions remain in the OKF bundle (there is no description write-back).

Setup

go install github.com/xSAVIKx/okf-skills/skills/okf-mongodb@latest
# …or: cd skills/okf-mongodb && go build -o okf-mongodb .

How to Use

1. Produce an OKF bundle

export MONGODB_URI="mongodb://user:pass@host:27017"
./okf-mongodb produce --db  --out  [--collections a,b] [--sample 100]
  • --uri (required): connection URI, or set MONGODB_URI (preferred — keeps the

secret out of argv). Credentials are stripped before being written to Resource.

  • --db (required): database name.
  • --out (required): output OKF bundle directory.
  • --collections: comma-separated allowlist (default: all).
  • --sample: documents to sample per collection for inference (default 100).

Re-running preserves enriched descriptions (incremental produce).

2. Ingest / verify

./okf-mongodb ingest --db  --bundle  [--sync]
  • Reports collections that are in the bundle but missing from the database (drift).
  • --sync: creates those missing collections (structure only; no documents, no

description write-back).

3. Inspect the schema (self-description)

./okf-mongodb schema

Prints the machine-readable JSON description used by okf-mcp to expose the skill.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Databases