Google Ads Intent Mcp
by davidmosiahcommunityv0.1.1
2
An MCP server and CLI for analyzing Google Ads search-term CSV exports to classify intent, identify waste, and draft dry-run negative-keyword plans. It keeps analysis local and avoids live account changes, with optional LLM-backed refinement off by default.
From the registry: Dry-run-first Google Ads search-term intent analyzer and negative-keyword MCP for agents.
Install & configure
Prerequisites
- optionalInstall pipxInstall pipx to run the published Python CLI as an isolated command.
https://pypi.org/project/google-ads-intent-mcp/$ pipx install "google-ads-intent-mcp[mcp]" - optionalOptional LLM backend setupLLM refinement is off by default. If you want the optional OpenAI-backed refinement path, install the openai package and provide an OpenAI API key. Without this, the server still works using the default heuristic classifier.
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `google-ads-intent-mcp` MCP server into my current AI client (that's you).
Optional prerequisites:
- Install pipx — Install pipx to run the published Python CLI as an isolated command. Run: `pipx install "google-ads-intent-mcp[mcp]"` (https://pypi.org/project/google-ads-intent-mcp/)
- Optional LLM backend setup — LLM refinement is off by default. If you want the optional OpenAI-backed refinement path, install the openai package and provide an OpenAI API key. Without this, the server still works using the default heuristic classifier.
Canonical MCP server config (stdio transport):
- command: `google-ads-intent-mcp`
- args: []
- optional environment variables:
- `GOOGLE_ADS_INTENT_LLM`: Enable optional LLM/embeddings-backed refinement. Off by default; when unset, the heuristic classifier is used. (example: `1`)
- `OPENAI_API_KEY`: OpenAI API key for the optional LLM backend. Only needed if LLM refinement is enabled and you want actual backend calls instead of heuristic fallback. (example: `<your-openai-api-key>`)
- `GOOGLE_ADS_INTENT_LLM_MODEL`: Optional model name for the OpenAI-backed refinement path. Defaults to gpt-4o-mini if not set. (example: `<your-openai-model>`)
Note: Prefer installing the MCP-enabled extra via pipx: pipx install "google-ads-intent-mcp[mcp]". The MCP server runs over stdio with the command `google-ads-intent-mcp`. No environment variables are required for the default dry-run heuristic workflow.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: Prefer installing the MCP-enabled extra via pipx: pipx install "google-ads-intent-mcp[mcp]". The MCP server runs over stdio with the command `google-ads-intent-mcp`. No environment variables are required for the default dry-run heuristic workflow.
Tools (6)
google_ads_agent_manifest
Provides install and runtime guidance for agent clients
google_ads_connection_status
Checks CSV/API readiness without credentials
google_ads_privacy_audit
Reviews dry-run boundaries, account access, and export/privacy constraints
google_ads_classify_search_term
Classifies a single search term by intent
google_ads_analyze_search_terms
Analyzes batches of search terms from CSV-style data
google_ads_build_negative_plan
Builds a dry-run negative keyword plan
Environment variables
GOOGLE_ADS_INTENT_LLMEnables optional LLM-backed refinement pathOPENAI_API_KEYrequiredRequired to call the optional LLM backendGOOGLE_ADS_INTENT_LLM_MODELOptional model name for the LLM backend, defaulting to gpt-4o-miniPrerequisites
- • python3
Packages
google-ads-intent-mcp
pypiv0.1.1transport: stdio
Details
- Language
- Python
- License
- MIT
- Released
- Jul 3, 2026
- Last commit
- Jul 3, 2026
- Registry name
- io.github.davidmosiah/google-ads-intent-mcp
Categories
Related Servers
Labelhead Artist Momentum
Trending hip-hop artist momentum scores across four cultural dimensions.
78.5k
PostHog MCP Server
Official PostHog MCP Server for product analytics, feature flags, experiments, and more.
37.7k
Openmetadata Mcp
Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.
14.9k