# app.gridar/gridar SEO toolkit for Quebec sites: audits, Google.ca rankings, keywords, AI-search visibility. - **Type:** MCP server - **Trust:** 60/100 (B), scored on the content rubric - **Verification:** community-indexed — nobody has claimed this listing - **Version:** 0.7.0 - **Author:** app.gridar - **License:** Unknown - **Endpoints:** streamable-http https://mcp.gridar.app/mcp - **Source:** https://github.com/TokDar2410621/blog-dashboard - **Endpoint health:** reachable (last checked 2026-09-25T22:16:49.952Z, 4 samples) — uptime is not a security property and is not part of the trust score - **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport) ## Trust 60/100 (B), scored on the content rubric - Publisher verified: no - Install scripts: nothing suspicious found - Prompt-injection scan: clean - Obfuscation scan: clean - Evidence age: 4 days ## Security scan - **Status:** clean - **Scanned:** 2026-10-01T02:06:10.080Z - **Version scanned:** HEAD - **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it. ## Tools 40 declared. Statically extracted from the shipped source — a floor on the surface, not a census. - `gridar-mcp` — SEO toolkit for Quebec sites: audits, Google.ca rankings, keywords, AI-search visibility. - `gridar_get_me` — Return the authenticated user's plan, current monthly article quota and remaining usage. - `gridar_list_sites` — List the sites belonging to the user (id, domain, hosting mode, default language). - `gridar_list_articles` — List articles on a given site. Optional filters: status, language, limit. - `gridar_get_article` — Return the full content (HTML + metadata) of a single article identified by site_id and slug. - `gridar_generate_article` — Generate a new SEO-optimized article on the given site. Consumes one article from the user's monthly quota (or one credit). Returns the generated content and th - `gridar_generate_sister_article` — Translate + adapt an existing article into another language and publish it as a sibling sharing the same translation_group (so hreflang alternates wire up autom - `gridar_audit_article` — Run the SEO auditor on raw content. Returns a 0-100 score plus actionable suggestions (length, keyword density, headings, links, meta). - `gridar_get_brief` — Build a content brief for a target keyword: search intent, outline, entities to cover, FAQ candidates, E-E-A-T signals. - `gridar_list_keywords` — List the tracked keywords for a site with their latest recorded ranking. - `gridar_snapshot_keywords` — Trigger a fresh ranking snapshot for all tracked keywords on a site. Returns the count of positions recorded. - `gridar_weekly_digest` — Return the weekly digest for a site (traffic, ranking, content decay) over the last 7 days. - `gridar_get_site` — Return full configuration of one site: integrations status, default language, knowledge base, competitors, GSC connection, autopilot config, author E-E-A-T fiel - `gridar_update_site` — Update editable site fields (name, description, knowledge_base, competitors, default_language, author_bio, author_credentials, public_blog_domain). Pass only th - `gridar_create_article` — Create a manually-authored article on a hosted site (no AI generation, no quota consumed). Use this when the user already has content to publish via the dashboa - `gridar_update_article` — Patch fields of an existing article (title, content, excerpt, status, cover_image, author, slug). Works on all site modes: hosted, external (Postgres), WordPres - `gridar_delete_article` — DESTRUCTIVE: permanently delete an article. Works on all site modes: hosted, external, WordPress, Shopify, and Webflow. CMS-side deletes are forced (no trash). - `gridar_track_keyword` — Add a keyword to track on a site. SERP position is snapshotted daily by the rank_snapshot cron. Reactivates the row if it was previously soft-deleted. - `gridar_untrack_keyword` — Soft-delete a tracked keyword (sets is_active=False). Historical SerpRank snapshots are preserved. - `gridar_suggest_keywords` — Ask Claude to suggest new tracked keywords for the site, anchored on RAG memory + homepage scrape (not just brand name). - `gridar_suggest_competitors` — Auto-detect likely SEO competitors for the site based on homepage + tracked keywords. - `gridar_analyze_competitors` — Analyze the SERP top 10 for a keyword: average word count, common headings, entity coverage, gap analysis. - `gridar_serp_analyze` — SERP Analyzer: fetch the top 10 organic results for a keyword and compute per-URL metrics (word count, h1/h2/h3 count, FAQ presence, video embed) plus averages. - `gridar_ai_visibility_summary` — AI Visibility tracker: returns aggregated metrics describing how often the site is cited in LLM responses (ChatGPT, Perplexity, Gemini, SearchGPT, Claude). Outp - `gridar_run_ai_visibility` — Trigger an AI Visibility check series for a site's tracked prompts. Creates one AiVisibilityResult per (prompt, engine) pair across all 5 engines (ChatGPT, Perp - `gridar_get_content_decay` — Find articles whose GSC impressions / clicks dropped significantly over the last N days. Suggests refresh / expand / redirect actions. - `gridar_find_broken_links` — Crawl the site articles + check outgoing links. Returns list of 4xx/5xx/timeouts. - `gridar_check_hreflang` — Validate hreflang tags on a site (translation_group consistency) OR on a raw HTML payload. - `gridar_detect_cannibalization` — Find pairs of articles on a site that compete for the same intent / keywords. Cross-language and cross-status aware. - `gridar_suggest_internal_links` — AI suggestions for internal-link insertions on a target article, anchored on the site's content corpus. - `gridar_bulk_audit` — Run the SEO audit across ALL published articles of a site in parallel (Gemini). Returns aggregated scores + top issues. Can take 30-60s on large sites. - `gridar_check_readability` — Score content readability (Flesch-Kincaid, ARI) in FR or EN. - `gridar_check_plagiarism` — Run originality / plagiarism check on the content (Tier 4 plan). - `gridar_keyword_research` - `gridar_page_speed` — Run PageSpeed Insights on a URL. Returns Core Web Vitals + suggestions. - `gridar_people_also_ask` — Harvest People-Also-Ask questions from Google SERP for a keyword. Useful to seed FAQ schemas. - `gridar_link_opportunities` — Surface candidate sites for backlink outreach on a keyword. Queries Serper for 'best sites' + resources / blogs variants, de-duplicates by domain, fil - `gridar_gsc_queries` — Pull top GSC queries (impressions / clicks / position) for a single article page over the last N days. Requires the article `slug`; the site must have GSC conne - `gridar_get_autopilot` — Return autopilot config for a site: enabled flag, weekly_count, last_run_at, next_run_at, last_error. - `gridar_set_autopilot` — Configure autopilot. Pass only the fields you want to change. ## Install **Verdict: review** — Installable, but 2 things to check first: No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it. **Cautions** (coverage gaps and advisories — never blocking) - No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it. - No publisher has proved control of this listing; it is indexed, not vouched for. **Config** (claude-code): ```json "{\n \"mcpServers\": {\n \"gridar\": {\n \"type\": \"http\",\n \"url\": \"https://mcp.gridar.app/mcp\"\n }\n }\n}" ``` ## Blast radius Moderate to extensive — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: deletes data; runs on someone else's infrastructure. - Floor 32, ceiling 56 (tier: unknown) - `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low. - This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score. ## Machine-readable views of this entry - Signed JSON: https://forgeregistry.com/api/v1/packages/app.gridar%2Fgridar - Install plan: https://forgeregistry.com/api/v1/packages/app.gridar%2Fgridar/install-plan - Alternatives: https://forgeregistry.com/api/v1/alternatives/app.gridar%2Fgridar - HTML page: https://forgeregistry.com/registry/app.gridar%2Fgridar - MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan` ## About this document Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.