Neuton Actors MCP Server
Pricing
from $5.00 / 1,000 workflow results
Neuton Actors MCP Server
Use Neuton's public data Actors from ChatGPT, Claude, Cursor, and other MCP clients through one searchable, cost-controlled gateway.
Pricing
from $5.00 / 1,000 workflow results
Rating
0.0
(0)
Developer
Ashwin Prasad
Maintained by CommunityActor stats
0
Bookmarked
1
Total users
0
Monthly active users
2 days ago
Last modified
Categories
Share
Give ChatGPT, Claude, Cursor, VS Code, or another MCP client one endpoint for Neuton's public data Actors. Search the live catalog, inspect the right input, run an Actor with a spending cap, and receive structured rows without adding every scraper separately.
MCP endpoint: https://neuton--neuton-actors-mcp-server.apify.actor/mcp
Connect and test
- Add the endpoint above as a remote Streamable HTTP MCP server.
- Authenticate with Apify OAuth or keep your Apify token in the client's secure connector settings.
- Ask:
Find a Neuton Actor for Greenhouse jobs, inspect its input, then run it for Stripe with at most 5 results and a $0.25 charge cap.
The server exposes five tools. Search and inspection are free; gateway-funded runs cost $5 per 1,000 returned workflow results. Clients that send their own customer token pay the selected Actor's normal Store price instead.
The catalog covers jobs and recruiting, company and compliance research, finance and government data, academic publications, apps and reviews, automotive and local data, ecommerce, and developer or RAG workflows.
Why use this instead of adding every Actor separately?
AI clients perform better with a small, stable tool set. This server exposes five tools while discovering newly published Neuton Actors automatically:
search_neuton_actors: find the right Actor for a goal or data source.get_neuton_actor: inspect example input, pricing, and the Store page.list_neuton_categories: browse the current portfolio by data lane.run_neuton_actor: start an allowlisted Actor with a hard spending cap.get_neuton_run: poll a run and retrieve a bounded result sample.
Only healthy public Actors owned by neuton can run through this gateway. Under-maintenance Actors are excluded automatically.
Always inspect an Actor before the first run. Keep the first result limit small and set max_total_charge_usd for every call.
Connect from ChatGPT
- Open Settings > Apps & Connectors > Advanced settings and enable Developer mode.
- Choose Create and enter the MCP URL shown on this Actor's Apify page, ending in
/mcp. - Select OAuth or Apify bearer-token authentication when prompted.
- Add the connector, start a new chat, and select Neuton Actors from the tools menu.
- Ask the first-workflow prompt above before increasing limits.
ChatGPT fixes the available tool list when a connector is created. Recreate the connector only if this server adds or removes MCP tools; newly published Neuton Actors appear without recreating it.
Connect from Claude Desktop
Add a remote MCP connection using the Actor's /mcp URL and your Apify API token as a bearer token. Clients that support custom headers may also send X-Apify-Customer-Token; this makes downstream runs use that Apify account directly. Without the extra header, the gateway runs the selected Actor and bills only returned workflow results through this MCP Actor.
Never paste an API token into a prompt or commit it to source control. Store it in the client's secure connector or environment settings.
Generic MCP configuration
Use these values in any MCP client that supports remote Streamable HTTP:
{"name": "neuton-actors","url": "https://neuton--neuton-actors-mcp-server.apify.actor/mcp","transport": "streamable-http","headers": {"Authorization": "Bearer ${APIFY_TOKEN}","X-Apify-Customer-Token": "${APIFY_TOKEN}"}}
The final public URL is verified after deployment. Use the URL displayed on the Actor page if it differs from this standard Apify hostname.
Output
Tool responses are structured JSON. Search returns ranked Actor names, categories, descriptions, and Store URLs. Inspection returns example input and pricing. Run and poll responses return the Actor name, run ID, status, dataset ID, billing mode, item count, a bounded result sample, and the Console run URL for debugging.
Authentication, cost, and privacy
- ChatGPT and OAuth clients use gateway billing at $0.005 per returned workflow result. Discovery and Actor inspection are not charged events.
- Clients that securely send
X-Apify-Customer-Tokenuse customer-funded mode and pay the selected Neuton Actor's published price directly. - Neuton's private owner token is supplied only by the Apify runtime and is never embedded in this server or returned to a client.
run_neuton_actordefaults to a $1 total charge cap and rejects caps over $25.- Result previews are limited to 100 dataset rows. Use the returned dataset ID for larger authorized workflows.
- The server does not accept arbitrary third-party Actor IDs.
- Use public data responsibly and follow applicable laws, privacy rules, website terms, and platform policies.
Responsible use
Use the gateway only for lawful public-data workflows. Do not use it to collect sensitive personal data, evade access controls, violate website terms, or make automated high-impact decisions without appropriate review.
Search and SEO terms
Relevant terms include Apify MCP server, ChatGPT scraping MCP, Claude data tools, jobs data MCP, academic research MCP, compliance data MCP, app reviews MCP, automotive data MCP, and structured data for AI agents.
Local development
python3 -m venv .venvsource .venv/bin/activatepip install -r requirements.txtpython -m unittest discover -s tests -vAPIFY_TOKEN="your-token" python -m src
The local endpoint is http://127.0.0.1:4321/mcp unless APIFY_CONTAINER_PORT specifies another port. The server uses the lightweight Apify API client because it orchestrates existing Actors and does not scrape pages itself.