Site Search Opener
NPM · SITE-SEARCH-OPENER-MCP
SEO and competitor research from sitemaps and feeds, robots.txt respected, Google link fallback.
Available components
Last scanned (19 hours ago)
Scores higher than 38% of npm servers
Category Marketing and SEO
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 30 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 7 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability75
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1279 tokens (~182/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage94
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 82% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 28 Oct 26 +25
- Malware scan: unverified → pass ▲ security
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → 0.86 ▲ functional
- 27 Oct 26 45
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Analysed npm/site-search-opener-mcp@1.1.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 93 packages
| Packages resolved | 93 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
build-project-file Build a project file ~112
Builds a project file (JSON) with own and competitor domains for one or more projects. Domains are checked first and only working ones are kept. The file imports straight into the Site Search Opener web app (Settings > Export/Import Projects > Import) and can be passed back to run-recipe.
| Name | Type | Req | Description |
|---|---|---|---|
| merge_with_json | string | – | An existing project file to add these projects to |
| projects | array | yes | – |
| validate | boolean | – | Check every domain returns HTTP 200 before adding it |
No output schema declared.
No examples provided.
check-urls Check that URLs work ~63
Checks domains, folders or full URLs and reports the HTTP status (200 means it works), redirects and the final address. Use it before adding domains to a project.
| Name | Type | Req | Description |
|---|---|---|---|
| urls | array | yes | Domains like example.com, folders like example.com/blog/, or full URLs |
No output schema declared.
No examples provided.
google-links Make Google search links ~211
Builds Google (or Bing) site: search links for a keyword and a list of domains, or for a recipe. The links are for the user to click; they open in the user's own browser. This tool does not search or read results.
| Name | Type | Req | Description |
|---|---|---|---|
| after | string | – | YYYY-MM-DD |
| before | string | – | YYYY-MM-DD |
| engine | string | – | – |
| exact | boolean | – | Wrap each keyword in quotes |
| exclude | array | – | Words to exclude |
| filetype | string | – | pdf, docx, xlsx and so on |
| keywords | array | – | One or more keywords. Several keywords become one OR group (or one link each for inurl:) |
| operator | string | – | – |
| own | array | – | Your own domain, used by recipes that exclude it |
| recipe | string | – | Use a recipe's query instead of operator and filters |
| targets | array | – | Domains or folders, for example competitor.com or competitor.com/blog/ |
No output schema declared.
No examples provided.
list-recipes List research recipes ~95
Lists ready-made research recipes. With no options it shows a short start-here list (one per team) and how many more each team has. Pass a team for that team's full list, or all for every recipe. Each recipe says what it finds and whether it reads sitemaps or gives Google links.
| Name | Type | Req | Description |
|---|---|---|---|
| all | boolean | – | Every recipe for every team |
| team | string | – | Only this team's recipes |
No output schema declared.
No examples provided.
run-recipe Run a research recipe ~208
Runs a team recipe across many domains. Sitemap recipes read each site's own sitemap and feeds (robots.txt respected) and return one combined table; sites without usable sitemaps get Google links instead. Google-only recipes return links. Domains come from targets or from a project file.
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | – |
| keywords | array | – | Keyword(s). Some recipes need one, semantic-depth needs two |
| limit_per_domain | integer | – | – |
| page_details | integer | – | Per domain, fetch this many top pages for HTTP status, title and description |
| project_json | string | – | A project file from build-project-file or the web app export |
| project_name | string | – | Which project in the file. Default: the first one |
| recipe | string | yes | Recipe id from list-recipes |
| since | string | – | Override the recipe's start date, YYYY-MM-DD |
| targets | array | – | Domains or folders. Leave empty to use project_json |
No output schema declared.
No examples provided.
save-file Save a file ~66
Saves a project file, CSV or Markdown table to your computer, in /tmp/Documents/Site Search Opener. Existing files are never overwritten; a number is added instead.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | – |
| file_name | string | yes | For example competitor-pages.csv or projects.json |
No output schema declared.
No examples provided.
site-inventory List a site's pages from its sitemap ~243
Reads one domain's own sitemap.xml and RSS or Atom feeds (robots.txt respected) and returns its pages as a table with URL, title, description, last modified date and HTTP status. Filter by keyword, URL text or date. If the site has no usable sitemap, it returns Google links instead.
| Name | Type | Req | Description |
|---|---|---|---|
| folders | boolean | – | Include a count of pages per top folder |
| format | string | – | – |
| keywords | array | – | Keep pages whose URL or title contains all words of any keyword |
| limit | integer | – | Rows to return |
| older_than | string | – | Keep pages last modified before YYYY-MM-DD |
| page_details | integer | – | For this many top rows, fetch the page for HTTP status, title and description |
| since | string | – | Keep pages modified on or after YYYY-MM-DD |
| subdomains | array | – | Also read these subdomains, for example docs or help |
| target | string | yes | A domain or folder, for example competitor.com or competitor.com/blog/ |
| url_contains | array | – | Keep pages whose URL path contains any of these, for example /blog/ or case-stud |
No output schema declared.
No examples provided.
How do I install the Site Search Opener MCP server?
Site Search Opener runs locally as an npm package, launched with npx -y site-search-opener-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · site-search-opener-mcp
claude mcp add albertalbs-site-search-opener-mcp -- npx -y site-search-opener-mcp
What is the Site Search Opener MCP server?
Site Search Opener is an MCP server listed in the public MCP registry as io.github.albertalbs/site-search-opener-mcp. SEO and competitor research from sitemaps and feeds, robots.txt respected, Google link fallback. This page covers its npm package (site-search-opener-mcp).
Is the Site Search Opener MCP server safe to use?
Site Search Opener scores 70 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Site Search Opener MCP server expose?
Site Search Opener exposes 7 tools: list-recipes, check-urls, build-project-file, google-links, site-inventory, and 2 more. Their descriptions and schemas cost roughly 998 tokens of context every time the server is loaded.
Is the Site Search Opener MCP server still maintained?
Site Search Opener is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Site Search Opener MCP server under?
Site Search Opener declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.