MCP server that wraps the Dagster GraphQL API — manage runs, assets, schedules, sensors, and backfills from any MCP client
Nothing to run from here
Medical Mcps 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.
99/100
trust score
12
tools declared
remote
at its publisher
—
calls last 7d
What it does
MCP servers for biological and medical APIs
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http medical-mcps https://mcp.cloud.curiloo.com/tools/everycure-kg/mcp
# 2 — ask your agent for something these tools do
# everycure_kg_execute_cypher, everycure_kg_get_schema, everycure_kg_get_stats and 9 more
Medical Mcps costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
PAAll 1 server
pascalwhoop1 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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http medical-mcps https://mcp.cloud.curiloo.com/tools/everycure-kg/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
12 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.
Execute a Cypher query against the Every Cure Matrix Knowledge Graph. IMPORTANT: This is a readonly connection. Only SELECT/READ queries are allowed. Write operations (CREATE, UPDATE, DELETE, MERGE) will fail. Available databases: everycure-v0.13.0 (latest), everycure-v0.12.0, everycure-v0.11.0, everycure-v0.10.0, everycure-0.4.8, ... Args: query: Cypher query string
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| parameters | no | — | |
| database | no | — |
Get the database schema including node labels, relationship types, and property keys. This is useful for understanding the structure of the graph database before writing queries. Args: database: Database version to query (defaults to latest: everycure-v0.13.0) Returns: JSON with schema information including: - labels: List of all node labels in the database
| Parameter | Type | Required | Notes |
|---|---|---|---|
| database | no | — |
Get database statistics including node count and relationship count. Args: database: Database version to query (defaults to latest: everycure-v0.13.0) Returns: JSON with statistics including: - node_count: Total number of nodes in the database - relationship_count: Total number of relationships in the database
| Parameter | Type | Required | Notes |
|---|---|---|---|
| database | no | — |
Get lists of supported node types and relationship types. Helps agents understand what node types and relationship types are available in the database. Returns both full lists from the database and curated "common" lists filtered for meaningful biomedical pathway discovery. The "common" lists exclude ontology noise, procedures, and other non-meaningful entities, focusing on t
| Parameter | Type | Required | Notes |
|---|---|---|---|
| database | no | — |
Get neighborhood of a node with optional filtering. Returns neighbors connected to the specified node, optionally filtered by relationship types and neighbor node labels. Args: node_id: Node identifier (e.g., "MONDO:0007113") relationship_types: Filter by relationship types (e.g., ["treats", "causes"]) node_labels: Filter neighbors by labels (e.g., ["Drug", "D
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node_id | string | yes | — |
| relationship_types | no | — | |
| node_labels | no | — | |
| max_hops | integer | no | — |
| limit | integer | no | — |
| database | no | — |
Get neighborhood statistics (degree, relationship type distribution). Returns statistical information about a node's neighborhood including total degree, relationship type distribution, and neighbor label distribution. Args: node_id: Node identifier (e.g., "MONDO:0007113") max_hops: Maximum distance from source node (1 = direct neighbors only) database: Databa
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node_id | string | yes | — |
| max_hops | integer | no | — |
| database | no | — |
Get neighborhood sorted by evidence strength or other criteria. Returns neighbors sorted by evidence strength (if available) or by relationship count/publication count. This helps prioritize the most relevant connections. Args: node_id: Node identifier (e.g., "MONDO:0007113") sort_by: Sort criterion ("evidence_strength", "publication_count", or "relationship_count
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node_id | string | yes | — |
| sort_by | string | no | — |
| relationship_types | no | — | |
| node_labels | no | — | |
| max_hops | integer | no | — |
| limit | integer | no | — |
| database | no | — |
Get list of supported metapaths for path finding. Returns information about all available metapaths that can be used with find_paths_by_metapath. These are biochemically sound patterns that prevent path explosion in the highly connected graph. Each metapath includes: - name: Human-readable name - description: What the metapath represents - pattern: List of node types
No parameter schema on file.
Find paths between two nodes using a predefined metapath. IMPORTANT: Only predefined metapaths are allowed to prevent path explosion in this highly connected graph. Custom path patterns are not supported. To discover available metapaths, use get_supported_metapaths(). To see what node types and relationship types are available in the database, use get_supported_types().
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_id | string | yes | — |
| target_id | string | yes | — |
| metapath_name | string | yes | — |
| max_paths | integer | no | — |
| database | no | — |
Find drugs for a disease using predefined metapaths. Searches for drugs that treat or are associated with a disease using multiple metapaths. Can include direct treatment relationships and/or indirect relationships via targets and pathways. Args: disease_id: Disease identifier (e.g., "MONDO:0007113") include_indirect: If True, include indirect paths via targets/pa
| Parameter | Type | Required | Notes |
|---|---|---|---|
| disease_id | string | yes | — |
| include_indirect | boolean | no | — |
| exclude_contraindicated | boolean | no | — |
| max_paths_per_metapath | integer | no | — |
| database | no | — |
Find diseases associated with a drug using metapaths. Searches for diseases that are indications, contraindications, or adverse events for a given drug. Args: drug_id: Drug identifier (e.g., "CHEMBL123" or "UMLS:C0017302") include_indications: Include diseases the drug treats include_contraindications: Include diseases where drug is contraindicated inc
| Parameter | Type | Required | Notes |
|---|---|---|---|
| drug_id | string | yes | — |
| include_indications | boolean | no | — |
| include_contraindications | boolean | no | — |
| include_adverse_events | boolean | no | — |
| database | no | — |
Find paths between two nodes using a custom metapath pattern. Allows users to specify custom metapath patterns like: "Drug->directly_physically_interacts_with->Protein->gene_product_of->Gene" All node types and relationship types are validated against Biolink Model to ensure they exist before constructing the query. IMPORTANT: For safety, max_hops is limited to 5 by default
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_id | string | yes | — |
| target_id | string | yes | — |
| metapath_pattern | string | yes | — |
| max_paths | integer | no | — |
| max_hops | integer | no | — |
| database | no | — |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 Medical Mcps 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 99 / 100
Release 0.1.22 · scanned 6 Oct 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 score99
Findings2 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digest2dc22d3bf39daa3966da07121ef3ae7218597d0cc75600bd6ac9471b4c82a657
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest2dc22d3bf39daa39
Scanned2026-10-06
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.1.22.
0.1.22
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 Medical Mcps 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.