Chroma’s official MCP server: vector search and collection management for RAG workflows.
Nothing to run from here
Krusgraph 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.
35
tools declared
—
trust score
remote
at its publisher
—
calls last 7d
What it does
Turn Microsoft Fabric tables into an explainable graph and a GraphQL API.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http krusgraph-mcp https://krusgraph.com/mcp
# 2 — ask your agent for something these tools do
# list_workspaces, list_sources, list_tables and 32 more
Krusgraph costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
KRAll 1 server
krusgraph1 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. Its publisher asks you to sign in with OAuth: run /mcp in Claude Code and pick this server, and it opens a browser for that once.
claude mcp add --scope user --transport http krusgraph-mcp https://krusgraph.com/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 — the only sign-in is its publisher’s own, with OAuth.
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
35 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.
The Fabric workspaces the signed-in account can see, with id, name and capacity. The id or the name identifies the workspace in every tool.
Takes no parameters.
Lakehouses, warehouses, SQL databases, Snowflake databases, mirrored databases (Snowflake, Azure SQL, Cosmos DB, SAP, ...), mirrored Databricks catalogs and mirrored catalogs in a Fabric workspace (id or name), plus existing API for GraphQL items. The display name or id identifies the source.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
Tables and columns (with types) in one schema of a source. Read-only. tables narrows the answer to names or patterns (["sales_*"]); detail is "auto" (full up to 60 tables, then a summary with the column count per table), "full" or "summary".
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| schema | string | no | — |
| tables | array | no | — |
| detail | string | no | — |
Infer keys and relationships for the source's tables. Returns the summary, each relationship with the rule that produced it (K0–K5 / R0–R4), ambiguous columns to confirm, keyless tables, names read through the synonym table, and a Mermaid ER diagram. Pass keys for composite keys ({"order_items":…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
| detail | string | no | — |
| mermaid | boolean | no | — |
Check the plan's keys and relationships against the rows, read-only: is each key unique and free of NULLs, and does every reference find its target (orphan count)? Returns counts and a verdict per key and relationship.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| max_items | integer | no | — |
The plan with the decisions made about it and its checks, as one JSON file to keep in your own repository, plus a short Markdown report and what needs attention first. Each key and relationship has a review status (proposed, accepted, rejected or open, with a reason, set through decisions:…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| decisions | array | no | — |
| previous | object/string | no | — |
| validate | boolean | no | — |
| tables | array | no | — |
| max_items | integer | no | — |
The first n rows (at most 20) of one table, read-only, so the meaning of columns can be checked before deciding on keys or relationships. Long text values are shortened. Columns whose name looks like personal data (names, e-mail, phone, national id, address, birth date; one rule per pattern) come…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| table | string | yes | — |
| schema | string | no | — |
| n | integer | no | — |
| show_personal_data | boolean | no | — |
Create a Fabric API for GraphQL item over the source's tables with the inferred relationships — or update the item of that name in place. Creates one item; never deletes an item. When an API of that name exists, the field names it has for the same relationships (the same columns in the same…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| name | string | yes | — |
| schema | string | no | — |
| writable | boolean | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
| allow_removals | boolean | no | — |
Rayfin (Fabric Apps) connector entity classes + schema.ts for the source's tables, with inferred keys and @one/@many relationships (sourceFields/targetFields spelled out). Returns {path: content}; nothing is deployed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| connector | string | no | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
| relationships | boolean | no | — |
The inferred entity types, keys and relationships as a Fabric IQ ontology (preview) draft: a summary with the rule behind every key and link, the binding checklist, a Turtle file the portal's Import ontology accepts, and the generation-2 item definition (TMDL parts) ready for POST /ontologies or…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| name | string | no | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
Create the Fabric IQ ontology (preview) item from the plan, or update the item of that name in place; never deletes. dry_run=true (the default) returns the definition parts and the REST call without creating anything.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| name | string | yes | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
| dry_run | boolean | no | — |
The plan as a Power BI semantic model in TMDL: one table per source table in Direct Lake mode on the source's SQL analytics endpoint, relationships with cardinality and filter direction (one active path per table pair, the rest inactive with the reason), keyless tables without relationships into…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| name | string | no | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
An existing semantic model in the workspace (name or id) against the plan for the source it reads: the relationships the model lacks, the ones a rule of the plan or the data contradicts (with that rule or count), other cardinality, filters in both directions, active where the plan says inactive or…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| model | string | no | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| check_data | boolean | no | — |
| max_items | integer | no | — |
| tmdl | object | no | — |
How two tables connect through the plan's relationships: the shortest chain of hops with the rule per step and a ready T-SQL SELECT … JOIN … with quoted identifiers (equally short paths are all listed). When no path exists it says so and suggests which relationship is missing, as a confirmed…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| start | string | yes | — |
| end | string | yes | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
The plan as a graph, from metadata only (no data queries): each table's role (fact, dimension, bridge, isolated) with the numbers behind it, the ten most central tables (in/out degree, betweenness, PageRank), subject areas, cycles and table pairs with more than one path (where a Power BI model…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
| detail | string | no | — |
Columns that could point at another table's key but are in no relationship, ranked by name similarity, type and triangular closure, then the best check (default 15) counted against the data: the share of the column's values that exist in the target key and how many distinct values it has.…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| check | integer | no | — |
Hand-over documentation for the source: every table with columns and types, keys and relationships with their rules, keyless tables, ambiguous columns and the ER diagram, with an empty Description column to fill in. With validate=true the counts from validate_plan (key uniqueness, orphans) are…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| validate | boolean | no | — |
| max_items | integer | no | — |
| tables | array | no | — |
A dbt sources file for the schema: unique and not_null on every inferred key column and relationships on every single-column relationship, in the syntax the dbt documentation gives (test arguments under arguments:; arguments_block=false writes them top-level for dbt before 1.10.5).…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| schema | string | no | — |
| source_name | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
| arguments_block | boolean | no | — |
Today's plan against the definition of an existing API for GraphQL item (name or id): new tables and columns, columns the API still maps that the source no longer has, relationships the plan no longer supports, and whether a create_backend with the same name would change anything. Changes nothing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| api | string | yes | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
| writable | boolean | no | — |
Create a Fabric SemanticModel item from the TMDL draft (Direct Lake on the source's SQL analytics endpoint), or update the item of that name in place; never deletes. dry_run=true (the default) returns exactly what would be sent — the parts and the REST call — without creating anything. Needs the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| name | string | yes | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
| dry_run | boolean | no | — |
Wide views over the plan in the source's SQL analytics endpoint or warehouse, only inside views_schema (created if missing): one per fact table with its dimensions joined in, one per header table (vw_orders: the orders with their customer and, once confirmed, the ship-to address), plus one per…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| schema | string | no | — |
| views_schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| dry_run | boolean | no | — |
A Fabric data agent over the source: the plan (tables, keys, relationships with rules, join paths) as its instructions, the source as its data source with the plan's tables selected, and 5–10 example question/T-SQL pairs, then published. Created through the public staging REST API; re-running…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| name | string | yes | — |
| schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| publish | boolean | no | — |
| show_personal_data | boolean | no | — |
| dry_run | boolean | no | — |
A Fabric notebook (PySpark) that builds clean silver tables from a lakehouse's tables, generated from the plan:
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| schema | string | no | — |
| silver_schema | string | no | — |
| order_by | object | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
| show_personal_data | boolean | no | — |
Create a Fabric notebook item with the silver_notebook_draft notebook, attached to the source lakehouse, or update the notebook of that name in place; never deletes, and creating it runs nothing (the notebook runs when someone runs it in Fabric). dry_run=true (the default) returns the notebook and…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| name | string | yes | — |
| schema | string | no | — |
| silver_schema | string | no | — |
| order_by | object | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
| show_personal_data | boolean | no | — |
| dry_run | boolean | no | — |
Materialized lake views in Spark SQL for a lakehouse with schemas, generated from the plan: one wide view per fact table in gold_schema, over the silver tables create_silver_notebook writes, with its dimensions joined in over the safest many-to-one paths, and CONSTRAINT ... CHECK ... ON MISMATCH…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| schema | string | no | — |
| silver_schema | string | no | — |
| gold_schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
| show_personal_data | boolean | no | — |
Create a Fabric notebook item with the gold_views_draft notebook, attached to the lakehouse, or update the notebook of that name in place; never deletes, and creating it runs nothing: the views are created when the notebook runs, and it stops before writing over a source table, a silver table or…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| name | string | yes | — |
| schema | string | no | — |
| silver_schema | string | no | — |
| gold_schema | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
| show_personal_data | boolean | no | — |
| dry_run | boolean | no | — |
A ready Fabric notebook and pipeline that every night read the lakehouse's schema, compare the plan with the one saved by the last run (plan_drift's and lineage's logic, used as a library), save the new plan in a table in the lakehouse (krusgraph.plans), and send a short summary ("column X in…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| schema | string | no | — |
| name | string | no | — |
| at | string | no | — |
| time_zone | string | no | — |
| library_ref | string | no | — |
Create the drift_monitor_draft notebook and pipeline in the workspace, or update the items of those names in place, and add the daily schedule to the pipeline unless one at the same time exists; never deletes, and no secret is written anywhere (the webhook address is a pipeline parameter the user…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| name | string | yes | — |
| schema | string | no | — |
| at | string | no | — |
| time_zone | string | no | — |
| library_ref | string | no | — |
| schedule | boolean | no | — |
| dry_run | boolean | no | — |
The items create_backend, create_semantic_model, create_silver_notebook, create_drift_monitor and create_gold_views would create, as files in Fabric's Git format: one folder per item named <name>.<type> with its .platform and definition files (graphql-definition.json, definition.pbism and…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| schema | string | no | — |
| items | array | no | — |
| names | object | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| tables | array | no | — |
| silver_schema | string | no | — |
| gold_schema | string | no | — |
| views_schema | string | no | — |
| writable | boolean | no | — |
| show_personal_data | boolean | no | — |
Everything needed to start an app on a created API for GraphQL item, read from its definition: a Lovable prompt describing the data model and the main views, a connection description, five GraphQL queries that walk the relationships, and the manual portal steps (introspection, permissions).…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| api | string | yes | — |
For an existing API for GraphQL item (name or id): what is in place and what is missing before an app can use it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| api | string | yes | — |
Which Fabric objects in the workspace build on the source's tables: GraphQL APIs (from their definition), semantic models (from their TMDL definition), views on the SQL analytics endpoint (INFORMATION_SCHEMA.VIEW_TABLE_USAGE) and data agents (named in their definition). Returns a graph (nodes:…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| schema | string | no | — |
| table | string | no | — |
Types, fields and relationships of an existing API for GraphQL item (name or id), in the names a query uses — read from the item's definition, so it works without introspection; these are the names a GraphQL query uses.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| api | string | yes | — |
A query for a question in Swedish or English about the given tables: T-SQL over the safest join path of the plan (each step with the rule behind its relationship), and with api (an API for GraphQL item over the source) the GraphQL query in that API's field names, or why GraphQL cannot answer it…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| source | string | yes | — |
| question | string | yes | — |
| tables | array | yes | — |
| schema | string | no | — |
| api | string | no | — |
| keys | object | no | — |
| confirmed | array | no | — |
| show_personal_data | boolean | no | — |
Run a read-only GraphQL query against a Microsoft Fabric API for GraphQL item (name or id) in the workspace, see https://learn.microsoft.com/fabric/data-engineering/api-graphql-overview. Query fields are named <type>s, e.g. { customers(first: 5) { items { customer_id name } } }; relationships…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace | string | yes | — |
| api | string | yes | — |
| query | string | no | — |
| variables | object | no | — |
| question | string | no | — |
| tables | array | no | — |
| source | string | no | — |
| schema | string | 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 Krusgraph 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: —
—Grade not published
No rule-by-rule report on file for this release
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.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither: the repository linked on this page is where this record was collected from, not a copy of what the address serves, so it is not graded in its place. So there is no grade — not a withheld one, an unmeasured one.
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 0.8.0.
0.8.0
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 Krusgraph 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.