Local-first knowledge graph for token-efficient code review through MCP and CLI
Nothing to run from here
Flowspec 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
1
downloads a day
local
runs on your machine
40
downloads in 30d
What it does
MCP server for FlowSpec — exposes project specs to Claude Code
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user flowspec-mcp '--' npx -y flowspec-mcp
# 2 — ask your agent for something these tools do
# flowspec_list_projects, flowspec_get_json, flowspec_get_project and 29 more
Flowspec costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
JKAll 1 server
jktfe1 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 Flowspec 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 Node.js — the current LTS (24) is the safe choice; npx 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 flowspec-mcp '--' npx -y flowspec-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 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
32 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.
List all FlowSpec projects with names and dates
No parameter schema on file.
Get the full JSON spec for a FlowSpec project (optimised for Claude Code consumption)
No parameter schema on file.
Get project data (nodes, edges, screens) for a FlowSpec project
No parameter schema on file.
Search for nodes by label across all projects, optionally filtered by type
No parameter schema on file.
Get screen/region/element structure for a FlowSpec project (lightweight alternative to full JSON)
No parameter schema on file.
Create a new FlowSpec project. Before building from a codebase, scan source files for @flowspec annotations (left by the codebase-indexer skill) to avoid re-discovering already-indexed elements.
No parameter schema on file.
Add a node (datapoint, component, transform, or table) to a project. Check source files for @flowspec annotations first — they contain pre-indexed element definitions (e.g. // @flowspec dp-name: type, source, constraints).
No parameter schema on file.
Update a node\
No parameter schema on file.
Connect two nodes with an edge type (flows-to, derives-from, transforms, validates, contains)
No parameter schema on file.
Run orphan node and duplicate label analysis on a project
No parameter schema on file.
Validate data flow semantics: DataPoint sources, Transform I/O, Component references, type matching, and circular dependencies
No parameter schema on file.
Update a project name or replace its entire canvas state
No parameter schema on file.
Delete a FlowSpec project
No parameter schema on file.
Remove a node and all its connected edges from a project
No parameter schema on file.
Remove an edge from a project
No parameter schema on file.
Import JSON specification to create/merge nodes, edges, and screens. If the codebase has @flowspec annotations, incorporate them into the spec before importing to avoid duplicating pre-indexed elements.
No parameter schema on file.
Apply automatic hierarchical layout (Dagre) to organize nodes
No parameter schema on file.
Upload an image and get its URL with auto-detected dimensions
No parameter schema on file.
Create a new wireframe screen with optional image
No parameter schema on file.
Update screen properties (name, image)
No parameter schema on file.
Delete a wireframe screen and all its regions
No parameter schema on file.
Add a region to a screen with % coordinates and element IDs
No parameter schema on file.
Update region position, size, label, or element IDs
No parameter schema on file.
Remove a region from a screen
No parameter schema on file.
Update edge type, label, or handle positions
No parameter schema on file.
Clone a project for backup or branching
No parameter schema on file.
List all decision trees for a project
No parameter schema on file.
Get a decision tree with full node/edge structure
No parameter schema on file.
Delete a decision tree from a project
No parameter schema on file.
Analyse a decision tree: depth, orphans, outcomes, under-branched decisions
No parameter schema on file.
Get the Boring Logic board for a project — a separate canvas of input/output/process/decision nodes sketching data logic
No parameter schema on file.
Save (create or replace) the Boring Logic board for a project
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- 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 Flowspec 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 5.5.2 · scanned 14 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
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digesta352e6ae4f2348a4e64e4c883f8680b166ce459c65669ff6b4e5feebc25c7307
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 surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (30 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>".
19 of the 30 recovered tools are registered only when TOOLS_MODE === 'all' holds (dist/server.js:56) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 11.
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.
11 tools are registered unconditionally · 19 more only when TOOLS_MODE === 'all' holds (dist/server.js:56) — typically when a key or option is configured. All 30 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| flowspec_list_projects | no tags | |
| flowspec_get_json | no tags | |
| flowspec_get_project | no tags | |
| flowspec_search_nodes | no tags | |
| flowspec_get_screen_context | no tags | |
| flowspec_create_project | no tags | |
| flowspec_create_node | no tags | |
| flowspec_update_node | no tags | |
| flowspec_create_edge | no tags | |
| flowspec_analyse_project | no tags | |
| flowspec_validate_project | no tags | |
| flowspec_update_project conditional | no tags | |
| flowspec_delete_project conditional | no tags | |
| flowspec_delete_node conditional | no tags | |
| flowspec_delete_edge conditional | no tags | |
| flowspec_import_json conditional | no tags | |
| flowspec_auto_layout conditional | no tags | |
| flowspec_upload_image conditional | no tags | |
| flowspec_create_screen conditional | no tags | |
| flowspec_update_screen conditional | no tags | |
| flowspec_delete_screen conditional | no tags | |
| flowspec_add_region conditional | no tags | |
| flowspec_update_region conditional | no tags | |
| flowspec_remove_region conditional | no tags | |
| flowspec_update_edge conditional | no tags | |
| flowspec_clone_project conditional | no tags | |
| flowspec_list_decision_trees conditional | no tags | |
| flowspec_get_decision_tree conditional | no tags | |
| flowspec_delete_decision_tree conditional | no tags | |
| flowspec_analyse_decision_tree conditional | no tags |
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 digesta352e6ae4f2348a4
Scanned2026-10-14
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 5.5.2. Pin a release below and the command asks for exactly that one.
5.5.2
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 Flowspec 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.