From nanotars-parallel
Configures Parallel AI web research tools for NanoTars agent containers via MCP servers. Enables quick web search and deep research with citations; guides API key setup, plugin install, and restart.
npx claudepluginhub terrifiedbug/nanotars-skills --plugin nanotars-parallelThis skill uses the workspace's default tool permissions.
Configures Parallel AI web research for agent containers using their HTTP-based MCP servers. Agents get tools for quick web search and deep research tasks.
Integrates Parallel AI MCP servers into ClaudeClaw for quick web searches using Search API and deep research with Task API. Useful for non-blocking web research in AI agents.
Adds Brave Search API access to NanoTars agent containers for web search in research, current events, and fact-checking. Guides free API key setup with verification steps.
Adds n8n workflow automation integration to NanoTars agents, enabling webhook-triggered monitoring workflows to avoid token-intensive polling. Guides n8n MCP server setup, API key config, and env variables.
Share bugs, ideas, or general feedback.
Configures Parallel AI web research for agent containers using their HTTP-based MCP servers. Agents get tools for quick web search and deep research tasks.
Before installing, verify NanoTars is set up:
[ -d node_modules ] && echo "DEPS: ok" || echo "DEPS: missing"
docker image inspect nanoclaw-agent:latest &>/dev/null && echo "IMAGE: ok" || echo "IMAGE: not built"
if grep -q "ANTHROPIC_API_KEY\|CLAUDE_CODE_OAUTH_TOKEN" .env 2>/dev/null || [ -f "$HOME/.claude/.credentials.json" ]; then echo "AUTH: ok"; else echo "AUTH: missing"; fi
If any check fails, tell the user to run /nanotars-setup first and stop.
grep "^PARALLEL_API_KEY=" .env 2>/dev/null && echo "KEY_SET" || echo "KEY_MISSING"
[ -d plugins/parallel ] && echo "PLUGIN_EXISTS" || echo "PLUGIN_MISSING"
If already configured, ask the user if they want to reconfigure or just verify.
Ask the user:
Do you have a Parallel AI API key, or should I help you get one?
If they need one:
- Go to https://platform.parallel.ai
- Sign up or log in
- Navigate to API Keys section
- Create a new API key
- Copy the key and paste it here
Wait for the API key.
sed -i '/^PARALLEL_API_KEY=/d' .env
echo "PARALLEL_API_KEY=THE_KEY_HERE" >> .env
Sync to container environment:
cp .env data/env/env
cp -r ${CLAUDE_PLUGIN_ROOT}/files/ plugins/parallel/
By default this plugin is available to all groups and channel types. To restrict access, edit plugins/parallel/plugin.json and set:
"groups" to specific group folder names (e.g., ["main"]) instead of ["*"]"channels" to specific channel types (e.g., ["whatsapp"]) instead of ["*"]Ask the user if they want to restrict access. Most users will keep the defaults.
npm run build
nanotars restart # or launchctl on macOS
Send a message in your channel like:
The agent now has Parallel AI search and deep research tools. Quick search is used freely; deep research asks for permission first.
plugins/parallel/mcp.json has the MCP server entries and PARALLEL_API_KEY is in .envPer-group overrides: If a specific group needs a different Parallel API key, add PARALLEL_API_KEY=... to groups/{folder}/.env. See /create-skill-plugin for details.
rm -rf plugins/parallel/sed -i '/^PARALLEL_API_KEY=/d' .env
cp .env data/env/env