DATABASES / MongoDB
MongoDB Search and AI
Chooses between Atlas Search, Vector Search, Automated Embedding and hybrid search, and creates indexes only after explicit approval.
“Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions. Use this skill when users need to build search functionality for text-based queries (autocomplete, fuzzy matching, faceted search), semantic similarity (embeddings, RAG applications), or combined approaches. Also use when users need text containment, substring matching ('contains', 'includes', 'appears in'), case-insensitive or multi-field text search, or filtering across many fields with variable combinations. Provides workflows for selecting the right search type, creating indexes, constructing queries, and optimizing performance using the MongoDB MCP server.”
01 / THE REASONING
Why this made the selection.
- Index creation follows a fixed sequence: explain the configuration, show the JSON, ask for a name and get explicit approval before calling create-index.
- Without create, update or delete tools it switches to read-only mode and gives the user the complete index JSON instead.
02 / THE REVIEW RECORD
What we actually inspected.
Source review has boundaries.
A clear record is more useful than a “safe” badge.
Material inspected
- skills/mongodb-search-and-ai/SKILL.md (core principles, workflow, anti-patterns, edge cases)
- README.md (plugin and direct skill installation)
- LICENSE Apache-2.0 text
Our findings
- Discovery checks the cluster's MongoDB version with atlas-inspect-cluster before recommending an index.
- Hybrid search merges pipelines with $rankFusion or $scoreFusion, per the file.
Not established by this review
- The installer was not run, and the skill was not executed against a project or service. No MCP tool call or query was run.
- The references/ files and README.community.md were not opened.
- Not executed: it was not installed or run.
The review applies to the material and revision named here. A newer upstream release can change its behavior.
03 / PUT IT TO WORK
Add a skill to your workflow.
DOCUMENTED COMMAND
npx skills add mongodb/agent-skillsRun in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above.
- The README documents npx skills add mongodb/agent-skills for the skills alone; it does not configure an MCP server. The mongodb-atlas plugin bundles the skills with the hosted Atlas MCP server.
- The command does not pin revision c370a63b27075008a92134686b24af3817edeb00. Compare the installed SKILL.md and references with that revision.
- Approve each index the agent proposes; the file requires explicit approval before create-index.
Before you start
- Node.js and npm for the documented Skills installer
- A configured MongoDB MCP server and a deployment the agent may query
04 / FOLLOW THE EVIDENCE
The source trail.
Our notes are separate from the original resource.
Check upstream before adopting a new version.
- Skill definition ↗Checked
https://github.com/mongodb/agent-skills/blob/c370a63b27075008a92134686b24af3817edeb00/skills/mongodb-search-and-ai/SKILL.md
Supports: summary, upstreamDescription, whySelected, limitations, access, review
https://github.com/mongodb/agent-skills/blob/c370a63b27075008a92134686b24af3817edeb00/README.md
Supports: install, compatibility
- Repository licence ↗Checked
https://github.com/mongodb/agent-skills/blob/c370a63b27075008a92134686b24af3817edeb00/LICENSE
Supports: license
https://raw.githubusercontent.com/mongodb/agent-skills/c370a63b27075008a92134686b24af3817edeb00/skills/mongodb-search-and-ai/SKILL.md
Supports: bestFor, review.notTested