Redirecting to documentation...
If you are not redirected automatically, click here.
Model Context Protocol server for accessing Keywords AI data from your AI assistant
Use the hosted endpoint where each user provides their own API key:
{ "mcpServers": { "keywords-ai": { "url": "https://mcp.keywordsai.co/api/mcp", "headers": { "Authorization": "Bearer YOUR_KEYWORDS_AI_API_KEY" } } } }
Run locally for development - simplest setup:
git clone https://github.com/Keywords-AI/keywordsai-mcp.git cd keywordsai-mcp npm install && npm run build
Configure your MCP client (~/.cursor/mcp.json):
~/.cursor/mcp.json
{ "mcpServers": { "keywords-ai": { "command": "node", "args": ["/path/to/keywordsai-mcp/dist/lib/index.js"], "env": { "KEYWORDS_API_KEY": "your_api_key" } } } }
Deploy to Vercel with API key stored as environment variable. No client-side key needed:
git clone https://github.com/Keywords-AI/keywordsai-mcp
vercel deploy --prod
KEYWORDS_API_KEY
Configure your MCP client:
{ "mcpServers": { "keywords-ai": { "url": "https://your-project.vercel.app/mcp" } } }
list_logs
get_log_detail
list_traces
get_trace_tree
list_customers
get_customer_detail
list_prompts
get_prompt_detail
list_prompt_versions
get_prompt_version_detail
All list tools support powerful filtering:
{ "cost": {"operator": "gt", "value": [0.01]}, "model": {"operator": "", "value": ["gpt-4"]}, "customer_identifier": {"operator": "contains", "value": ["user"]}, "metadata__session_id": {"operator": "", "value": ["abc123"]} }
Operators: "" (equal), not, lt, lte, gt, gte, contains, icontains, startswith, endswith, in, isnull
""
not
lt
lte
gt
gte
contains
icontains
startswith
endswith
in
isnull