pwn-mcp-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@pwn-mcp-server render a multiwavelength cutout of the Crab Nebula with pulsar and SNR outline"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
pwn-mcp-server
An MCP server for pulsar wind nebulae (PWNe) and other nebulae. It lets an LLM client:
query catalogs: a bundled table of 37 well-studied PWNe and 16 showcase SNRs, H II regions and planetary nebulae, plus live SIMBAD, VizieR (Green's SNR catalogue, H.E.S.S. HGPS, Sharpless, WISE H II, Strasbourg-ESO PNe), the ATNF pulsar catalogue and CADC
render images: survey cutouts with pulsar, SNR and PWN overlays, including native-resolution Canadian Galactic Plane Survey (CGPS) 1420 and 408 MHz mosaics from CADC, multi-wavelength panels, Galactic maps with the CGPS footprint, P–Ṗ and population plots
compare colour spaces: the perceived colour of nebular spectra under the CIE 1931 2° and CIE 1964 10° standard observers (xy, u′v′, CIELAB, sRGB, ΔE2000, dominant wavelength), with reddening and the scotopic (rod) response
Install and run
From PyPI with uv:
uvx --from pwn-mcp-server pwn-mcpRegister it with Claude Code:
claude mcp add pwn -- uvx --from pwn-mcp-server pwn-mcpOr run the container (stdio):
docker run -i --rm -v pwn-mcp-data:/data ghcr.io/wdconinc/pwn-mcp-serverOr from a checkout:
uv sync
uv run pwn-mcpTo inspect the tools interactively:
npx @modelcontextprotocol/inspector uvx --from pwn-mcp-server pwn-mcpClaude Code plugin
claude-plugin/ packages the server as the pwn-nebulae Claude Code plugin,
which runs it with uvx from the main branch. To try it from a checkout:
claude --plugin-dir ./claude-pluginConfiguration
Variable | Default | Meaning |
| unset |
|
|
| Timeout for remote services (s) |
| platform user cache dir | Cache for live queries and image cutouts (30-day TTL) |
|
| Where rendered PNGs are saved |
Related MCP server: quasar-mcp
Tools
Catalogs
Tool | What it does |
| Filter the bundled catalog by name, kind, PWN class, Galactic position, CGPS coverage, pulsar Ė |
| Full record: position, host SNR (Green), pulsar (ATNF), TeV counterpart (HGPS), CGPS coverage; |
| Objects around a name or position in the bundled table, Green, HGPS, Sharpless, WISE H II, PNe, ATNF |
| Whole-catalog queries with constraints, e.g. all type-F (filled-centre) remnants in Green |
| ATNF parameters for one pulsar |
| Whether a position is in the CGPS 1420/408 MHz footprint; optionally list CADC products |
| Available catalogs and provenance of the bundled tables |
Images and plots (each returns a PNG plus JSON metadata, including the saved path)
Tool | What it does |
| CGPS 1420/408 MHz, CGPS+VGPS, NVSS, SUMSS, DSS2, Pan-STARRS, IPHAS/VTSS/SHASSA Hα, AllWISE, ROSAT, Fermi |
| One survey around an object, with pulsar, host-SNR outline, PWN extent and neighbours |
| Panel grid of the same field in several surveys |
| Plane strip or all-sky map with the CGPS footprint, optionally over all Green SNRs |
| P–Ṗ diagram with PWN hosts highlighted and constant B, τ_c and Ė lines |
| Scatter of PWN properties (Ė, τ_c, distance, sizes in arcmin or pc, …) |
Colour (CIE 1931 2° vs CIE 1964 10°)
Tool | What it does |
| H II region, planetary nebula, SNR shock, Crab filaments/synchrotron/integrated, single lines, equal-energy white |
| Colour of a template or a custom spectrum (emission lines, synchrotron, blackbody, reddening) under each observer, with differences |
| xy and u′v′ diagrams with both spectral loci and the templates under each observer |
| The x̄ȳz̄ functions of both observers with the main nebular lines marked |
| sRGB swatches per observer next to each spectrum |
| A template spectrum with each observer's ȳ(λ) |
Resources: pwn://catalog/pwne, pwn://catalog/nebulae, pwn://lines, pwn://surveys,
pwn://references. Prompts: summarize_pwn, compare_nebula_colors.
Notes on the science
Bundled catalog. Only names, associations and PWN class (filled-centre, composite, relic,
bow-shock) in src/pwn_mcp/data/*_curated.csv are entered by hand. Every number in pwne.csv and
nebulae.csv is produced by scripts/build_local_catalog.py from SIMBAD, Green's catalogue
(VizieR VII/297, 2024 October version), the ATNF catalogue and the HGPS. Pulsar distances are the
ATNF DIST values. PWN sizes are only filled for filled-centre remnants, where Green's diameter is
the PWN size. Rebuild with:
uv run python scripts/build_local_catalog.pyCGPS. The footprint used for in_cgps is approximate: 52° ≤ l ≤ 192°, −3.5° ≤ b ≤ +5.5°,
plus the high-latitude extension. Use cgps_coverage(query_archive=true) for the actual mosaics.
cgps_1420 and cgps_408 cut out the DRAO mosaics at CADC (brightness temperature, K).
cgps_vgps_1420 uses the IRAP/CADE HiPS.
Colorimetry. Spectra are integrated on a 0.1 nm grid against the CIE tables from
colour-science. Template line strengths are representative
values relative to Hβ = 100, not measurements of a specific position; references are listed per
template. sRGB is defined for the 2° observer. For the 10° observer, XYZ₁₀ is treated as relative
to the 10° D65 white and adapted (CAT02) to sRGB white. That makes swatches comparable, but no
standard 10° sRGB exists. Line-dominated spectra are usually outside the sRGB gamut and are
desaturated toward white for display (in_srgb_gamut: false). The scotopic/photopic ratio uses
CIE 1951 V′(λ) and CIE 1924 V(λ). It explains why Hα-bright nebulae look grey by eye at the
telescope while [O III]-bright ones look greenish.
Development
uv sync
uv run ruff check . && uv run ruff format --check .
uv run pytest # offline unit and MCP integration tests
uv run pytest -m network # tests that contact SIMBAD, VizieR, ATNF, CADC and hips2fitsReleases. The version comes from git tags (hatch-vcs). Pushing a tag vX.Y.Z, or creating a
release in the GitHub UI, runs .github/workflows/release.yml. It builds the sdist and wheel,
attaches them to the GitHub release, publishes to PyPI via trusted publishing (when the repository
variable PUBLISH_TO_PYPI is true), and pushes ghcr.io/wdconinc/pwn-mcp-server:{X.Y.Z, X.Y, latest}.
License
MIT
Available Tools
20 toolscgps_coverageB
Is a position or named object inside the Canadian Galactic Plane Survey (1420 MHz, 408 MHz, HI)? Optionally list the actual CGPS data products at CADC.
Inputs: b, l, ra, dec, +2 more.
cone_searchC
Find catalogued SNRs, TeV sources, H II regions, PNe and pulsars around a position or named object.
Inputs: b, l, ra, dec, +4 more.
get_nebulaA
Full record for one nebula: position, PWN class, host SNR (Green catalogue), powering pulsar (ATNF: P, Ṗ, Ė, τ_c, B, distance), TeV counterpart (HGPS), CGPS coverage and the matching colour template. Unknown names fall back to SIMBAD.
Inputs: name (required), live.
get_pulsarB
ATNF pulsar catalogue parameters: period, Ṗ, spin-down power Ė, characteristic age, surface and light-cylinder fields, DM and distance, associations.
Inputs: name (required).
list_catalogsA
Catalogs available to cone_search and query_vizier, plus the bundled tables.
Inputs: no named parameters.
list_spectrum_templatesA
List synthetic nebular spectrum templates (H II region, planetary nebula, SNR shock, Crab Nebula filaments/synchrotron, single lines) and the known emission lines.
Inputs: no named parameters.
list_surveysA
Image surveys available to render_cutout / render_multiwavelength, with band, coverage, resolution and credit.
Inputs: no named parameters.
nebula_colorB
Perceived colour of a nebular spectrum under each observer: XYZ, xy, u'v', CIELAB, sRGB hex, dominant wavelength and purity, plus Δu'v' and ΔE2000 between observers and the scotopic/photopic ratio (rod sensitivity, relevant to visual observing).
Inputs: ebv, lines, fwhm_kms, template, +6 more.
plot_chromaticity_comparisonC
CIE 1931 xy and CIE 1976 u'v' diagrams showing each observer's spectral locus and where each nebula template falls under each observer.
Inputs: reddened, observers, templates.
plot_cmf_comparisonB
Overlay the x̄ȳz̄ colour-matching functions of the chosen observers, with the main nebular emission lines marked.
Inputs: observers.
plot_galactic_mapB
Map of bundled PWNe and other nebulae in Galactic coordinates with the CGPS footprint, optionally over the full Green SNR catalogue.
Inputs: kinds, label, highlight, projection, +2 more.
plot_nebula_spectrumC
Plot a template spectrum with each observer's luminance function ȳ(λ) overlaid.
Inputs: template (required), ebv, observers.
plot_populationB
Scatter plot of two properties of the bundled PWNe, coloured by PWN class (e.g. Ė vs τ_c, PWN size in pc vs age). Physical sizes use the ATNF distance. Axes go logarithmic automatically when the data span more than two decades.
Inputs: x, y, log_x, log_y.
plot_ppdotB
P–Ṗ diagram of pulsars with the PWN-powering pulsars highlighted by PWN class, and lines of constant magnetic field, characteristic age and spin-down power.
Inputs: include_atnf.
query_vizierC
Query a whole VizieR catalog with optional column constraints, e.g. all filled-centre (type F) or composite (type C) remnants in Green's SNR catalogue.
Inputs: catalog (required), limit, constraints.
render_color_swatchesB
Side-by-side sRGB swatches of each template's colour under each observer, next to its spectrum.
Inputs: reddened, observers, templates.
render_cutoutC
Survey image around a nebula with the pulsar, host-SNR outline (Green diameter), PWN extent and neighbouring catalogued objects overlaid. CGPS images are native-resolution cutouts of the DRAO mosaics at CADC; other surveys come from CDS hips2fits.
Inputs: b, l, ra, dec, +8 more.
render_multiwavelengthB
Panel grid of the same field in several surveys (radio, optical, IR, X-ray, gamma-ray). Surveys that do not cover the position are shown as empty panels with the reason.
Inputs: b, l, ra, dec, +4 more.
search_nebulaeA
Search the bundled catalog of pulsar wind nebulae and showcase nebulae (SNRs, H II regions, planetary nebulae) by name, type, Galactic position, CGPS coverage or pulsar properties. Use cone_search or query_vizier for the full live catalogs.
Inputs: kind, b_max, b_min, l_max, +7 more.
server_infoA
Report the server version and which optional capabilities are enabled.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 20 tools
Most tools have clearly distinct targets: catalog lookups (search_nebulae, get_nebula, get_pulsar, cone_search, query_vizier), image rendering (render_cutout vs render_multiwavelength), and analytics. The main softness is in the colour/spectrum cluster, where nebula_color, plot_chromaticity_comparison, plot_cmf_comparison, plot_nebula_spectrum and render_color_swatches all operate on the same observer/template space and could be mis-picked. Position-based search_nebulae versus cone_search is also close, though the bundled-vs-live distinction is stated.
The dominant pattern is a clear snake_case verb_noun (list_surveys, get_nebula, render_cutout, plot_ppdot, search_nebulae, query_vizier). A handful of outliers break the pattern: cone_search is noun_verb, while server_info, cgps_coverage and nebula_color have no verb at all. Readable and predictable overall, but not fully uniform.
20 tools is at the heavy end for a read-only data/visualisation server, and the surface is split across three sub-domains (catalog queries, image rendering, colour science). The six plot_* tools plus three colour-specific tools make the set feel like it grew by accretion rather than being tightly scoped. Each tool is individually defensible, but consolidation of the plotting/colour variants would help.
Coverage across the stated domain is strong: discovery (search_nebulae, cone_search, query_vizier), detail records (get_nebula, get_pulsar), survey discovery and coverage checks, single- and multi-band rendering, population plots, and a full spectral-to-colour pipeline. Minor gaps exist, such as no export/save path for rendered figures and no way to synthesise a custom spectrum beyond the fixed templates. Nothing that would obviously hard-block an agent.
Maintenance
Related MCP Connectors
Observational astronomy in one place
Offline observational astronomy: positions, rise/set, moon phases, eclipses, and seasons.
ESA Gaia MCP — the Gaia star catalogue, queried over the ESA TAP service.
Search, describe, render and measure volumes in point clouds and rasters stored in LumiDB.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables querying the ESA Gaia star catalogue (DR3) for astrometric and photometric data via cone searches, source ID lookups, and arbitrary ADQL queries over the TAP service.96 npmMIT
- FlicenseNot gradedqualityBmaintenanceIt equips LLM clients with roughly 200 live astronomy research tools spanning ALMA/NRAO, MAST, ESO, VO archives, SIMBAD/NED/VizieR, Splatalogue, NASA ADS, Data Lab, ZTF and imaging, with plots and images returned inline. Users can search and cross-match archives, identify spectral lines, pull literature and BibTeX, and run photometry, SED and variability analysis against real data.-
- AlicenseAqualityBmaintenanceEnables fetching and analyzing public Type Ia supernova Hubble diagrams, including covariance-aware binning, plotting, chi-squared evaluation, and flat LCDM/wCDM/w0waCDM fits with contour comparisons and optional HPC dispatch.211MIT
- AlicenseNot gradedqualityBmaintenanceEnables querying and analyzing spectroscopic galaxy survey data, including BAO/RSD compilations with cosmological fits and plots, SDSS SkyServer catalog queries and galaxy properties, and GSWLC-A2 catalog access and crossmatching.1MIT