content-schema-mcpSAFE
An open-source, local-first (MCP) server for Automated Schema org JSON-LD Generation, GA4 Metric Validation, llm.txt Auditing
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
📖 Official Architecture & Documentation: SEOSiri Content Schema Guide | Central MCP Directory
An open-source, local-first Model Context Protocol (MCP) server for Automated Schema.org JSON-LD Generation, GA4 Metric Validation, /llm.txt Auditing, and Content Stickiness Analytics.
💖 Sponsorship, B2B Custom Solutions & Attribution
👨💻 Lead Architect & Attribution
Designed and engineered by [Momenul Ahmad](https://github.com), Lead Architect and Founder of [SEOSiri](https://seosiri.com).
🚀 Capabilities & Tools (10 Production Tools)
- `generate_tech_article_schema`: Generates multi-entity TechArticle JSON-LD markup.
- `generate_faq_page_schema`: Compiles structured FAQPage JSON-LD schema blocks for voice search.
- `validate_ga4_report_metrics`: Validates GA4 metric and dimension compatibility.
- `calculate_content_stickiness_score`: Computes GA4 "Retention Gold" scores comparing Duration against Bounce Rate.
- `validate_llm_txt_formatting`: Audits presence and Markdown syntax structure of
/llm.txt. - `audit_rfc_9116_security_txt`: Audits RFC 9116
/.well-known/security.txtheaders. - `extract_structured_answer_snippets`: Extracts direct-answer snippets for Perplexity and SearchGPT.
- `sanitize_content_payload`: Strips script injections and unverified metadata.
- `get_live_schema_throughput_metrics`: Monitors system health and processing latency.
- `get_schema_server_specifications`: Returns protocol specs and capability matrices.
Quickstart
pip install -e . pytest tests/test_content_schema.py
🔌 Claude Desktop / Cursor Configuration
Add this block to your claude_desktop_config.json:
{
"mcpServers": {
"seosiri-content-schema": {
"command": "uv",
"args": [
"run",
"--github",
"SEOSiri-Official/content-schema-mcp",
"src/main_server.py"
]
99e3c8485e9cOBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add seosiri-content-schema-mcp -- uvx seosiri-content-schema-mcp
{
"mcpServers": {
"seosiri-content-schema-mcp": {
"command": "uvx",
"args": [
"seosiri-content-schema-mcp"
]
}
}
}Exposed tools (10)
10 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
audit_rfc_9116_security_txt | read | |
calculate_content_stickiness_score | read | |
extract_structured_answer_snippets | read | |
generate_faq_page_schema | read | |
generate_tech_article_schema | read | |
get_live_schema_throughput_metrics | read | ANALYTICS: Returns server operational health and performance metrics. |
get_schema_server_specifications | read | SPECIFICATIONS: Returns technical protocol details and tool capability matrices. |
sanitize_content_payload | read | Sanitizes incoming content strings, stripping scripts and malicious tags. |
validate_ga4_report_metrics | read | |
validate_llm_txt_formatting | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
99e3c8485e9cfull audit observations/trust-audit/mcp-server/seosiri-official__content-schema-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 99e3c8485e9c | SAFE | B | 89 | first audit |
Questions
What is the content-schema-mcp MCP server?
An open-source, local-first (MCP) server for Automated Schema org JSON-LD Generation, GA4 Metric Validation, llm.txt Auditing
What tools does content-schema-mcp expose?
10 in total: 10 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is content-schema-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does content-schema-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does content-schema-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as seosiri-content-schema-mcp.
How current is this page?
The grade is for one exact copy of the source (99e3c8485e9c), read on 2026-10-11. The repository is watched and re-audited when it changes.