# @neuronsearchlab/mcp

Recommendations, search, catalogue, analytics, and platform admin tools for NeuronSearchLab

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the package rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 1.0.0
- **Author:** com.neuronsearchlab
- **License:** MIT
- **npm:** @neuronsearchlab/mcp
- **Endpoints:** streamable-http https://console.neuronsearchlab.com/api/mcp
- **Source:** https://github.com/NeuronSearchLab/mcp
- **Endpoint health:** reachable (last checked 2026-08-27T03:22:41.654Z, 1 sample) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the package rubric
- Publisher verified: no
- Build provenance: verified attestation
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 19 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-08-09T13:40:36.204Z
- **Version scanned:** 0.6.2
- **CVEs:** none found by OSV at scan time

## Tools

40 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `get_recommendations`
- `get_auto_recommendations`
- `track_event`
- `upsert_item`
- `patch_item`
- `delete_items`
- `search_items`
- `explain_ranking`
- `get_account_plan`
- `list_contexts`
- `create_context`
- `update_context`
- `delete_context`
- `list_pipelines`
- `create_pipeline`
- `update_pipeline`
- `delete_pipeline`
- `list_rules`
- `create_rule`
- `update_rule`
- `delete_rule`
- `toggle_rule`
- `get_context`
- `get_pipeline`
- `activate_pipeline`
- `deactivate_pipeline`
- `clone_pipeline`
- `get_rule`
- `enable_rule`
- `disable_rule`
- `reorder_rules`
- `list_segments`
- `get_segment`
- `create_segment`
- `update_segment`
- `delete_segment`
- `get_segment_stats`
- `list_experiments`
- `get_experiment`
- `create_experiment`

## Install

**Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for.
**Cautions** (coverage gaps and advisories — never blocking)
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@neuronsearchlab/mcp\"\n      ],\n      \"env\": {\n        \"NSL_CLIENT_ID\": \"<YOUR_NSL_CLIENT_ID>\",\n        \"NSL_CLIENT_SECRET\": \"<YOUR_NSL_CLIENT_SECRET>\",\n        \"NSL_API_KEY\": \"<YOUR_NSL_API_KEY>\"\n      }\n    }\n  }\n}"
```
**Credentials it will ask for** (names only — Forge never holds a value):
- `NSL_CLIENT_ID` — Nsl Client ID (optional)
- `NSL_CLIENT_SECRET` — Nsl Client Secret (optional)
- `NSL_API_KEY` — Nsl API Key (optional)
Placeholders only. Forge never holds, brokers, or transmits a credential value — replace each <YOUR_NAME> in your own config file. Do not send a value back to Forge; no Forge endpoint accepts one.
- This entry needs 3 credentials (0 required). The generated config carries placeholders, so it will fail in the editor rather than at runtime if they are left unset.

## Blast radius

Critical blast radius — deletes data; holds an oauth grant.
- Floor 69, ceiling 69 (tier: critical)
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40neuronsearchlab%2Fmcp
- Install plan: https://forgeregistry.com/api/v1/packages/%40neuronsearchlab%2Fmcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40neuronsearchlab%2Fmcp
- HTML page: https://forgeregistry.com/registry/%40neuronsearchlab%2Fmcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.