ai.linkguard/linkguard-mcp
PYPI · LINKGUARD-MCP · SCANNED SEP 20
Backlink tools for AI assistants: redirect, Google index, and backlink health checks.
Available components
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 Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 1 of 22 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 121 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability68
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 738 tokens (~246/item across 3 items; 3 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 Management87
- Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 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
How do I install the ai.linkguard/linkguard-mcp server?
ai.linkguard/linkguard-mcp runs locally as a PyPI package, launched with uvx linkguard-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · linkguard-mcp
claude mcp add ai-linkguard-linkguard-mcp -- uvx linkguard-mcp
{
"mcpServers": {
"ai-linkguard-linkguard-mcp": {
"command": "uvx",
"args": [
"linkguard-mcp"
]
}
}
} {
"servers": {
"ai-linkguard-linkguard-mcp": {
"command": "uvx",
"args": [
"linkguard-mcp"
]
}
}
} codex mcp add ai-linkguard-linkguard-mcp -- uvx linkguard-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"ai-linkguard-linkguard-mcp": {
"type": "local",
"command": [
"uvx",
"linkguard-mcp"
],
"enabled": true
}
}
} openclaw mcp add ai-linkguard-linkguard-mcp --command uvx --arg linkguard-mcp
mcp_servers:
ai-linkguard-linkguard-mcp:
command: "uvx"
args: ["linkguard-mcp"] {
"McpServers": {
"ai-linkguard-linkguard-mcp": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"linkguard-mcp"
]
}
}
} assistant mcp add ai-linkguard-linkguard-mcp -t stdio -c uvx -a linkguard-mcp
{
"mcpServers": {
"ai-linkguard-linkguard-mcp": {
"command": "uvx",
"args": [
"linkguard-mcp"
]
}
}
} 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.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 −18
- Malware scan: pass → unverified ▼ security
- Stability: pass → 0.80 functional
- 17 Sept 26 0
- Stability: 0.97 → pass security
- 16 Sept 26 +16
- Malware scan: unverified → pass ▲ security
- 14 Sept 26 −14
- Malware scan: pass → unverified ▼ security
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Sept 26 −3
- Stability: pass → 0.80 functional
- 10 Sept 26 0
- Stability: 0.97 → pass security
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 20 Sept 2026 · Analysed pypi/linkguard-mcp@0.1.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 22 packages
| Packages resolved | 22 |
|---|---|
| Stale | 1 |
| 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 →
backlink_health_snapshot ~303
Full health verdict for one backlink: live, dofollow, indexed, SEO-healthy? Performs a comprehensive check of a single backlink by: 1. Fetching the donor page (using a real browser for JS-heavy sites). 2. Checking whether the donor is indexed in Google. 3. Parsing all links on the donor page to find references to your target. 4. Evaluating rel attributes (nofollow, sponsored, ugc), canonical tags, noindex signals, and outbound link dilution. 5. Producing a scored verdict (HEALTHY / AT_RISK / BROKEN) with specific issues and actionable recommendations. May use a real cloud browser for JavaScript-rendered donor pages. In that case, 5 tokens are debited from your LinkGuard balance. No debit occurs for static pages (HTML-only fetch). Use this tool when you need to: - Run a full audit on a specific backlink before including it in a report. - Diagnose why a backlink might not be passing SEO value. - Confirm that a newly placed backlink is live and properly attributed. - Generate evidence for a link-building outreach follow-up.
| Name | Type | Req | Description |
|---|---|---|---|
| donor_url | string | yes | The page that should contain the backlink (the donor site's page). Example: "https://example.com/blog-post" |
| target_url | string | yes | Your page that the backlink should point to. Example: "https://yoursite.com/landing" |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
backlink_index_check ~227
Check whether a backlink URL is indexed in Google. Queries XMLRiver's indexation API to determine if the given page appears in Google's index. Returns one of three statuses: - INDEXED — Google has the page in its index; includes the SERP title and meta description when available. - NOT_INDEXED — The page exists but Google has not (or no longer) indexed it, which means the backlink passes no link equity. - UNKNOWN — The check was inconclusive (API quota, timeout, etc.). Use this tool when you need to: - Verify that a donor page passing you backlinks is actually indexed. - Identify de-indexed donor pages that should be flagged in an audit. - Retrieve the SERP snippet for a donor page for competitive research. This tool is free (no token debit). Blocked URL categories (.gov, .mil, .edu, spam-shaped paths) return a 422 with a rejection reason.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The donor page URL to check. Example: "https://example.com/blog-post" |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
redirect_check ~171
Trace the full redirect chain of a URL and its SEO impact on backlinks. Follows every HTTP hop from the given URL to its final destination, detecting redirect types (301/302/307/308), meta-refresh, and JavaScript-based redirects. Returns an SEO-impact summary explaining whether the chain is clean, lossy, or broken. Use this tool when you need to: - Verify that a backlink URL still resolves correctly. - Identify unnecessary redirect hops that bleed link equity. - Detect redirect loops or truncated chains. - Confirm the final landing URL of a partner link. This tool is free (no token debit).
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The URL to trace. Bare domains are accepted (https:// is prepended automatically). Example: "https://example.com/old-page" |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
What is the ai.linkguard/linkguard-mcp server?
ai.linkguard/linkguard-mcp is listed in the public MCP registry as ai.linkguard/linkguard-mcp. Backlink tools for AI assistants: redirect, Google index, and backlink health checks. This page covers its PyPI package (linkguard-mcp).
Is the ai.linkguard/linkguard-mcp server safe to use?
ai.linkguard/linkguard-mcp scores 61 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 ai.linkguard/linkguard-mcp server expose?
ai.linkguard/linkguard-mcp exposes 3 tools: redirect_check, backlink_index_check, backlink_health_snapshot. Their descriptions and schemas cost roughly 701 tokens of context every time the server is loaded.
Is the ai.linkguard/linkguard-mcp server still maintained?
ai.linkguard/linkguard-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 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 ai.linkguard/linkguard-mcp server under?
ai.linkguard/linkguard-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.