Vantage changelog

icon_url

— → https://vantagemcp.dev/favicon.svg

version

1.11.1 → 1.14.0

file

absent → published

https://raw.githubusercontent.com/vantagemcp/vantage-mcp/HEAD/AGENTS.md

+ # AGENTS.md+ Notes for coding agents working in this repository.+ ## What this is+ Vantage is a Python MCP server that checks whether AI answer engines (ChatGPT, Gemini, Perplexity, Google AI+ Overviews) cite a domain. It exposes ten read-only tools. The hosted copy runs at `https://vantagemcp.dev/mcp`;+ this repo is the server only. Billing and account provisioning live in a separate internal service.+ ## Layout+ - `src/vantage_mcp/server.py`: tool definitions (`@mcp.tool`), the stdio and `--http` (Streamable HTTP) transports.+ - `src/vantage_mcp/dataforseo_client.py`: calls to the data provider and parsing of the answers it returns.+ - `src/vantage_mcp/auth.py`, `keys.py`, `store.py`: OAuth sign-in, API keys, SQLite usage and saved checks.+ - `src/vantage_mcp/research.py`: the monthly research run. `mailer.py`: the email that sends a copy of a key at sign-in.+ - `npm/`: the stdio wrapper published as `vantage-ai-visibility-mcp`; it connects to the hosted server.+ ## Run and check+ ```bash+ uv venv && uv pip install -e .+ export DATAFORSEO_USERNAME=... DATAFORSEO_PASSWORD=...+ python -m vantage_mcp.server          # stdio+ python -m vantage_mcp.server --http   # Streamable HTTP on VANTAGE_PORT (default 8420)+ ```+ CI here only checks that `vantage_mcp.server` imports. The fuller test suite is kept with the maintainers' working+ copy, so say in your pull request what you ran.+ ## Rules that matter+ - Every tool is read-only and returns structured data. Keep new tools read-only and annotated like the others.+ - Metering happens before the paid provider call. A call that is rejected must never cost money.+ - A tool's unit cost appears in its docstring and in the README tables. Change them together.+ - `analyze_citation_gap`'s `fix_brief` never contains the cited answer's text. Keep it that way.+ - Never commit credentials. Provider credentials come from the environment.

https://vantagemcp.dev/llms.txt

− - check_prompt_coverage - which of several prompts/keywords actually cite a specific domain, and which don't (up to 10 keywords per call); remembers each result and reports what changed since your last check− - analyze_citation_trend - month-by-month citation counts for a domain, so visibility trend over time is measurable− The live-answer tools (check_prompt_coverage, analyze_citation_structure and its batch form, analyze_citation_gap) take engine: chat_gpt (default), gemini or perplexity. check_prompt_coverage and analyze_citation_structure also take samples (1 to 5): answers change from run to run, so samples=3 reports "cited in 2 of 3 answers" instead of a single yes or no. Every answer carries the model and the time it was fetched.− The free checks cover ChatGPT, one answer per search. Gemini and Perplexity, several answers per search, up to ten searches at a time, change tracking and the fix brief are check_prompt_coverage and analyze_citation_gap, which need a free account.+ - get_supported_options - which engines, platforms and markets each tool accepts, and the per-call limits. Costs 0 units.+ - analyze_citation_coverage - which of several prompts/keywords actually cite a specific domain, and which don't (up to 10 keywords per call); remembers each result and reports what changed since your last check+ - analyze_citation_trend - month-by-month citation counts for a domain, optionally next to competitors' trends, so visibility trend over time is measurable+ The live-answer tools (analyze_citation_coverage, analyze_citation_structure and its batch form, analyze_citation_gap) take engine: chat_gpt (default), gemini or perplexity. analyze_citation_coverage and analyze_citation_structure also take samples (1 to 5): answers change from run to run, so samples=3 reports "cited in 2 of 3 answers" instead of a single yes or no. Every answer carries the model and the time it was fetched.+ The free checks cover ChatGPT, one answer per search. Gemini and Perplexity, several answers per search, up to ten searches at a time, change tracking and the fix brief are analyze_citation_coverage and analyze_citation_gap, which need a free account.

version

1.11.0 → 1.11.1

version

1.9.1 → 1.11.0

version

1.9.0 → 1.9.1