nemo-retriever-mcp
Skill3k starsChanged 18 days agoApache-2.0View on GitHub
Use when a task needs to search or add documents through NeMo Retriever MCP.
2 other projects use a version of this.
Trending
More talk lately.thin dataabout the whole repository
Most recently taken up by
- NVIDIA/nv-ingestword for word, first seen Oct 8, 2026
- NVIDIA/skillsword for word, first seen Oct 1, 2026
Who's talking about NVIDIA/NeMo-Retriever
- randerzander/reddbrowser“Update re-indexing notebook to include the same Gemma embedding model baseline used in the ReAct retrieval …”GitHub · Nov 3, 2026
- randerzander/reddbrowser“Improve scaling and eliminate need for SKU specific tuning with Jacob's heuristics PR”GitHub · Nov 3, 2026
- sudosubin/agents.nix“agent-skills.github.nvidia.nemo-retriever: init at 26.8.2”GitHub · Sep 30, 2026
- charlesbluca/NeMo-Retriever“[codex] Use OCRv2 package lang selectors”GitHub · May 11, 2026
- NVIDIA-AI-Blueprints/rag“Kheiss/prd additions”GitHub · Mar 11, 2026
The biggest 5 of 5 mentions linking to the repository that our crawl found. Each line is their own headline.
Other versions2 projects use a version of this.
Word for word · 2
- NVIDIA/skills★ 3.9k100% same
- NVIDIA/nv-ingest★ 3k100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- nemo-retrieverSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 2 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Use the NeMo Retriever MCP tools exposed under retriever instead of the retriever CLI.
- Very specific: line 18
Use query to search documents already available to Retriever.
- Distinctive: line 19
Never ingest documents that are already searchable, including documents in a prebuilt index.
- Very specific: line 21
Use ingest_documents only when required documents are not yet searchable and server-readable paths are explicitly available.
- Very specific: line 24
After ingestion completes, use query to retrieve evidence from the added documents.
- Very specific: line 26
Start with top_k=5 and format="hits".
- Distinctive: line 28
Read evidence hits from the tool response and ground your answer in them.
- Very specific: line 32
If query fails, inspect the error and retry with corrected parameters or a shorter equivalent query.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
NeMo Retriever MCP
Use the NeMo Retriever MCP tools exposed under retriever instead
of the retriever CLI.
The server exposes MCP tools, not MCP resources. Do not call
list_mcp_resources to discover documents or decide whether Retriever is
available; an empty MCP resource list is expected.
Workflow
- Use
queryto search documents already available to Retriever. - Never ingest documents that are already searchable, including documents in a prebuilt index.
- Use
ingest_documentsonly when required documents are not yet searchable and server-readable paths are explicitly available. Do not assume that paths visible to the agent are also readable by the Retriever server. - After ingestion completes, use
queryto retrieve evidence from the added documents. - Start with
top_k=5andformat="hits". Request more only when the first successful response does not contain enough evidence to answer the task. - Read evidence hits from the tool response and ground your answer in them.
- Preserve available document identifiers such as
document_id,source_id, orpdf_basename, along with page numbers, when the task requests citations or structured output. - If
queryfails, inspect the error and retry with corrected parameters or a shorter equivalent query. If it still fails, report the error before using another retrieval method.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

