Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
DICOM Agent is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
trust score
12
downloads a day
local
runs on your machine
30
downloads in 30d
What it does
Search, retrieve, store, view, measure and de-identify DICOM images over DIMSE and DICOMweb.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user dicom-agent-mcp '--' uvx dicom-agent-mcp
# 2 — ask your agent for something these tools do
# list_nodes, echo, search and 13 more
DICOM Agent costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
AMAll 1 server
arunmk-ms1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts DICOM Agent as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user dicom-agent-mcp '--' uvx dicom-agent-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take AZURE_DICOM_TOKEN (Bearer token for a DICOMweb node configured with token-env=AZURE_DICOM_TOKEN. Use any variable name you reference in --node.), DICOM_AGENT_MCP_DEID_KEY (Secret that makes de-identification pseudonyms and UIDs consistent across calls.) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
16 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
List the configured DICOM nodes (PACS, VNA, DICOMweb services) and their protocols.
Takes no parameters.
Check connectivity to a node (C-ECHO for DIMSE, a minimal QIDO-RS request for DICOMweb).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node | yes | — |
Search for patients, studies, series or instances (C-FIND or QIDO-RS).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node | yes | — | |
| level | string | no | Query/retrieve level. |
| filters | object | no | Matching keys, e.g. {"PatientID": "123", "Modality": "CT", "StudyDate": "20240101-20241231"}. |
| return_fields | array | no | Extra attributes to return besides the level defaults. |
| limit | integer | no | Maximum results to return. |
| offset | integer | no | Results to skip, for paging. |
Read instance-level metadata without downloading pixel data (WADO-RS metadata or C-FIND).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node | yes | — | |
| study_uid | yes | — | |
| series_uid | no | — | |
| sop_instance_uid | no | — | |
| fields | array | no | Limit or extend the returned attributes. |
| limit | integer | no | Maximum instances to return. |
Download a study, series or instance into the local cache (C-GET or WADO-RS). Returns file paths.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node | yes | — | |
| study_uid | yes | — | |
| series_uid | no | — | |
| sop_instance_uid | no | — |
Ask a DIMSE archive to send data to another DICOM node (C-MOVE).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node | yes | — | |
| destination | string | yes | Destination node name or an AE title known to the source archive. |
| study_uid | yes | — | |
| series_uid | no | — | |
| sop_instance_uid | no | — |
Send local DICOM files to a node (C-STORE or STOW-RS).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node | yes | — | |
| paths | array | yes | Local DICOM files or directories inside the allowed paths. |
Copy data between any two nodes, including DIMSE to DICOMweb, through the local cache.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source | string | yes | Node to read from. |
| destination | string | yes | Node to write to. |
| study_uid | yes | — | |
| series_uid | no | — | |
| sop_instance_uid | no | — |
List DICOM files in the local cache.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| study_uid | string | no | Only list files for this study. |
| limit | integer | no | — |
Read the full header of a local DICOM file. Pixel data is not loaded.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Path to a local DICOM file inside the allowed paths. |
| max_depth | integer | no | How deep to expand sequences. |
Render one frame of a local DICOM image as a PNG you can look at.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | yes | — | |
| frame | no | — | |
| window | no | — | |
| window_center | number | no | Explicit window center (overrides window). |
| window_width | number | no | Explicit window width (overrides window). |
| max_size | no | — |
Pixel value statistics in modality units (HU for CT): mean, std, min, max, percentiles and area in mm2.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | yes | — | |
| frame | no | — | |
| roi | no | Region of interest; omit for the whole frame. |
Measure a distance in mm between two pixel positions and give their patient coordinates.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | yes | — | |
| start | array | yes | [row, column] in pixels. |
| end | array | yes | [row, column] in pixels. |
| frame | no | — |
Check series geometry before measuring or reconstructing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paths | yes | — |
Reconstruct an axial, coronal or sagittal view from a stack of slices and render it as a PNG.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paths | yes | — | |
| plane | string | no | Plane to reconstruct. |
| index | integer | no | Slice index in the reconstructed plane; default is the middle. |
| series_uid | string | no | Series to use when the paths contain several. |
| window | no | — | |
| window_center | number | no | Explicit window center. |
| window_width | number | no | Explicit window width. |
| max_size | no | — |
Write de-identified copies of local DICOM files (basic confidentiality profile subset) to the cache.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paths | yes | — | |
| date_mode | string | no | Shift dates by a per-patient offset, or keep them. |
| keep_descriptions | boolean | no | Keep study/series descriptions and protocol names. |
| keep_private | boolean | no | Keep private tags. |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install DICOM Agent or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 0.1.0 · scanned 3 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest830970eb7ebe131186e54ad2e77cb60bb30b11c7eb2b692e480b774b1d9dd16a
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (16 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_nodes | no tags | |
| echo | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_metadata | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| retrieve | untrusted-inputexternal-sink | untrusted-input: keyword "download"; external-sink: declares readOnlyHint: false, openWorldHint: true |
| move | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| store | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| transfer | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| list_local_files | no tags | |
| read_local_metadata | no tags | |
| render_image | no tags | |
| pixel_statistics | no tags | |
| measure_distance | no tags | |
| check_geometry | no tags | |
| render_mpr | no tags | |
| deidentify | state-write | state-write: declares readOnlyHint: false |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest830970eb7ebe1311
Scanned2026-11-03
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
0.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish DICOM Agent can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.