Google Search Console integration for Model Context Protocol (MCP)
Nothing to run from here
budgetSEO 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.
93/100
tool-list score
16
tools declared
remote
at its publisher
—
calls last 7d
What it does
Affordable SEO & GEO data: rank tracking, keywords, competitors, AI visibility.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http budgetseo-mcp https://www.budgetseo.ai/api/mcp
# 2 — ask your agent for something these tools do
# get_seo_briefing, find_quick_wins, find_opportunities and 13 more
Its address takes AUTHORIZATION (Bearer token. ChatGPT, Claude, and Cursor complete OAuth on connect. Other clients send a Connect AI personal access token as "Bearer bseo_pat_...") in the Authorization header: add it to the entry your client keeps for it.
budgetSEO costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
BUAll 1 server
budgetseo1 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 budgetseo-mcp https://www.budgetseo.ai/api/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 asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: Authorization header — Bearer token. ChatGPT, Claude, and Cursor complete OAuth on connect. Other clients send a Connect AI personal access token as "Bearer bseo_pat_...".. You set it in your own client’s config, on your machine — this marketplace never holds it.
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
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.
Use this first when the user asks what to do with SEO today, what changed, or what to focus on. Returns the top actions, recent rank moves, plan limits, and the next automatic check.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | no | — |
| since | string | no | — |
Use when the user asks for low-hanging fruit, quick wins, or striking-distance keywords. Each result includes the estimated monthly clicks gained by moving up.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | no | — |
| limit | integer | no | — |
Use for best opportunities across quick wins, research ideas, competitor gaps, rank drops, and AI Overview citation gaps. Filter with kinds when the user names one of those.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | no | — |
| kinds | array | no | — |
| limit | integer | no | — |
List the user's BudgetSEO projects, keyword counts, whether a project is paused by the plan, and how many keyword slots remain.
No parameter schema on file.
Winners and losers over a recent window. Use for what moved, what dropped, or a weekly review. days defaults to 7.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | no | — |
| days | integer | no | — |
Deep context for one tracked keyword: ranking URL, history, SERP features, competitors, and a checklist. Use after a briefing when an agent can edit the page. Confirm with the user before changing the site.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keywordId | string | yes | — |
Competitors and how many tracked keywords each one outranks the user on. Uses saved competitor data only and never starts a paid lookup. keywordsAhead is null until that competitor has been checked.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | no | — |
Latest AI search snapshot and keywords where an AI Overview shows but does not cite the user. Pass projectId when the user has more than one project.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | no | — |
Add keywords to a project. Does not spend lookup credits; it uses the plan keyword slots. Confirm the keywords with the user first. countryCode defaults to the project market.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | yes | — |
| keywords | yes | — | |
| countryCode | string | no | — |
| device | string | no | — |
Remove one tracked keyword and its history. This cannot be undone. Confirm with the user before calling it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keywordId | string | yes | — |
Mark a briefing action done, dismissed, or snoozed. Call this after the user finishes or rejects an action so later briefings skip it. snoozeUntil is YYYY-MM-DD.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | yes | — |
| actionKey | string | yes | — |
| status | string | yes | — |
| note | string | no | — |
| snoozeUntil | string | no | — |
Find new keyword ideas for one project. This spends AI research usage and is available on Starter and Pro. Confirm with the user first. The project needs an audience set in the SEO Agent.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | yes | — |
Keyword ideas from one seed: volume, difficulty, and intent. Spends 6 lookup credits unless the result is already cached. Tell the user the cost and wait for a yes. This is not research_keywords.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| seed | string | yes | — |
| countryCode | string | no | Two-letter country code. Defaults to US. |
Volume, difficulty, and intent for keywords the user names. Spends 2 lookup credits. Tell the user the cost and wait for a yes. At most 20 keywords per call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keywords | array | yes | — |
| countryCode | string | no | Two-letter country code. Defaults to US. |
Organic keywords, estimated traffic, and top ranking URLs for a domain. Spends 4 lookup credits unless the result is already cached. Tell the user the cost and wait for a yes. countryCode defaults to US.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | — |
| countryCode | string | no | Two-letter country code. Defaults to US. |
Referring domains, backlink totals, and domain rank. Spends 3 lookup credits unless the result is already cached. Tell the user the cost and wait for a yes. spamScore is not a reason to disavow a list of URLs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | — |
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 budgetSEO 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: —
ATool-list grade · score 93 / 100
Release 1.0.0 · scanned 30 Oct 2026
Graded from the tools this server lists, not from its source code.
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 score93
Findings0 threat · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest3f7f1d717f9cfecbf2424071c01632700f35e3cbf2045c2d033f7f15799d454f
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
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 |
|---|---|---|
| get_seo_briefing | no tags | |
| find_quick_wins | no tags | |
| find_opportunities | no tags | |
| list_projects | no tags | |
| get_rank_changes | no tags | |
| get_keyword_action_plan | no tags | |
| get_competitor_overview | no tags | |
| get_ai_visibility | no tags | |
| track_keywords | state-write | state-write: declares readOnlyHint: false |
| untrack_keyword | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| update_recommendation | state-write | state-write: declares readOnlyHint: false |
| research_keywords | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| lookup_keywords | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| check_keywords | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| lookup_domain | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| lookup_backlinks | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
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 digest3f7f1d717f9cfecb
Scanned2026-10-30
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 1.0.0.
1.0.0
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 budgetSEO 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.