budgetSEO MCP server

• Registry nameai.budgetseo/budget-seo-mcpverified in the MCP registry

The registry name sits under budgetseo.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-30
• Tools16
• Server calls itselfbudgetseo
• Server version1.0.0
• Protocol version2025-06-18

On 2026-10-30 the server answered initialize and tools/list without a sign-in. First answer in 136 ms.

• Whether its tools do the product's job has not been judged yet.
• Checked on 6 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
• Answeredmeasuring6 of the 7 daily checks it takes to print a share
• Median first answer151 ms
• Space in an agent's context≈ 2,457 tokensthe definitions of all its tools (17), which an agent carries on every turn
• Tool definitionsB · 84 of 100
• Typed results17 of 17 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 16 of 17

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• get_seo_briefing

  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.

• find_quick_wins

  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.

• find_opportunities

  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.

• list_projects

  List the user's BudgetSEO projects, keyword counts, whether a project is paused by the plan, and how many keyword slots remain.

• get_rank_changes

  Winners and losers over a recent window. Use for what moved, what dropped, or a weekly review. days defaults to 7.

• get_keyword_action_plan

  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.

• get_competitor_overview

  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.

• get_ai_visibility

  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.

• track_keywords

  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.

• untrack_keyword

  Remove one tracked keyword and its history. This cannot be undone. Confirm with the user before calling it.

• update_recommendation

  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.

• research_keywords

  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.

• lookup_keywords

  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.

• check_keywords

  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.

• lookup_domain

  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.

• lookup_backlinks

  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.