CATNAP (Compile, Analyze, and Tally Neutralizing Antibody Panels) + the
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add mcp-catnap -- npx -y @pipeworx/mcp-catnap{
"mcpServers": {
"mcp-catnap": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-catnap"]
}
}
}MCP Servers overview
# @pipeworx/catnap
HIV-1 broadly neutralizing antibody potency (LANL CATNAP: IC50/IC80/ID50 across antibody-virus panels) plus HIV T-cell epitope and antibody-binding-site records (LANL HIV Molecular Immunology Database).
Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1573+ live data sources.
## Tools
- `catnap_search_neutralization(antibody?, virus?, limit?)` — antibody-virus neutralization measurements (IC50/IC80/ID50), the antibody's potency compared across viral strains. Censored bounds (`>150`, `<.05`) are returned as `censored: true` with `numeric_value: null` — never coerced to a number.
- `catnap_antibody_info(name, limit?)` — antibody metadata: epitope/binding region, structure (PDB), isolation paper, panel summary stats.
- `immunology_search(table, mab_name?, epitope?, protein_name?, limit?)` — T-cell epitopes (CTL/CD8+ or T-helper/CD4+) or antibody binding sites, queried live from LANL's own API.
## Auth
Keyless. `catnap_search_neutralization` and `catnap_antibody_info` return neutralization/antibody data ingested monthly from LANL's CATNAP bulk files (credentials injected by the gateway). `immunology_search` calls LANL's public JSON API directly on every call — no ingest.
## Data sources
- <https://www.hiv.lanl.gov/components/sequence/HIV/neutralization/index.html> (CATNAP) — antibody-virus neutralization panels (IC50/IC80/ID50), compiled by LANL from published papers. Monthly bulk tab-delimited files (`assay_*.txt`, `abs_*.txt`, `viruses_*.txt`), filename dated at each drop — the ingest scrapes the download page for the current links rather than hardcoding a date. Ingested by `workers/data-pipeline/src/datasets/catnap.ts` on a monthly cadence into `catnap_neutralization`, `catnap_antibodies`, `catnap_viruses` (see `supabase/migrations/170_catnap_neutralization.sql`).
- <https://www.hiv.lanl.gov/mojo/immunology/api/v2> (HIV Molecular Immunology Database JSON API) — CTL/CD8+, T-helper/CD4+ and antibody epitope/binding-site records. Keyless, queried live, no ingest.
## What to get right
- **Censored values are never coerced.** IC50/IC80/ID50 in the source are sometimes a bound (`>150` = not neutralized up to the highest concentration tested; `<.05` = fully neutralized at the lowest concentration tested), not a point estimate. Every measurement carries `_raw` (verbatim string), `_value` (numeric, `null` when censored) and `_censor` (`'<'`/`'>'`, `null` otherwise). A `>50` stored as `50` would invert a potency ranking.
- **Assay context travels with every value.** IC50/IC80 from different papers use different protocols and virus stocks — the tool always returns `reference`/`pubmed_id` and never implies cross-study comparability just because two values are both labelled "IC50".
- **Two different questions live in this one pack.** `catnap_search_neutralization`/`catnap_antibody_info` answer "how potent is this antibody" (CATNAP); `immunology_search` answers "where on the virus does this immune response target, and which HLA restricts it" (Immunology DB) — a different upstream database with its own record IDs.
## Refresh path
`workers/data-pipeline/src/datasets/catnap.ts`, registered in `workers/data-pipeline/src/datasets/index.ts`, `schedule: 'monthly'`. Re-fetches and re-parses all three CATNAP bulk files each run (the neutralization file is ~200k rows / ~16MB, chunk-upserted with a cursor across invocations); no stale-row delete — CATNAP accumulates measurements rather than retracting them.
## Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
```json
{
"mcpServers": {
"catnap": {
"url": "https://gateway.pipeworx.io/catnap/mcp"
}
}
}
```
### What this endpoint actually serves
`tools/list` at `https://gateway.pipeworx.io/catnap/mcp` returns the tools in the table
above **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,
`discover_tools`, `search_within`, `remember`/`recall` and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's `initialize` response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
`ask_pipeworx`, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed
directly, instead of just this one's:
```json
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
```
Both URLs reach the same gateway and the same 1573+ data sources. The
only difference is which pack's tools are listed **directly**; `ask_pipeworx`
reaches all of them from either one.
## Standalone (no gateway account)
This package also runs as a local stdio MCP server — no Pipeworx account, no
gateway round-trip:
```json
{
"mcpServers": {
"catnap": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-catnap"]
}
}
}
```
Or run it directly to confirm it starts:
```bash
npx -y @pipeworx/mcp-catnap
```
It speaks MCP over stdin/stdout and answers `initialize`/`tools/list`/`tools/call`
for **only** this pack's tools — none of the shared meta-tools the gateway
connection above adds. Same source, same tools, no ask_pipeworx routing.
## Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English —
this works on the pack endpoint above as well as on the full gateway:
```
ask_pipeworx({ question: "your question about Catnap data" })
```
The gateway picks the right tool and fills the arguments automatically.
## More
- [Docs and guides](https://pipeworx.io/docs)
- [pipeworx.io](https://pipeworx.io)
## License
MIT
What people ask about mcp-catnap
What is pipeworx-io/mcp-catnap?
+
pipeworx-io/mcp-catnap is mcp servers for the Claude AI ecosystem. CATNAP (Compile, Analyze, and Tally Neutralizing Antibody Panels) + the It has 0 GitHub stars and its last recorded update is dated 2026-09-14.
How do I install mcp-catnap?
+
You can install mcp-catnap by cloning the repository (https://github.com/pipeworx-io/mcp-catnap) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is pipeworx-io/mcp-catnap safe to use?
+
Our security agent has analyzed pipeworx-io/mcp-catnap and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains pipeworx-io/mcp-catnap?
+
pipeworx-io/mcp-catnap is maintained by pipeworx-io. The last recorded GitHub activity is dated 2026-09-14, with 0 open issues.
Are there alternatives to mcp-catnap?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy mcp-catnap to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/pipeworx-io-mcp-catnap)<a href="https://claudewave.com/repo/pipeworx-io-mcp-catnap"><img src="https://claudewave.com/api/badge/pipeworx-io-mcp-catnap" alt="Featured on ClaudeWave: pipeworx-io/mcp-catnap" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ
The fastest path to AI-powered full stack observability, even for lean teams.