
CoreClaw MCP server
Which MCP servers are CoreClaw's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-09
- Addresshttps://mcp.coreclaw.com/mcpnot in the official registry: answered when asked
No entry in the official MCP registry names this server. It answered on coreclaw.com when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.
- Stateanswerschecked 2026-10-27
- Tools42
- Server calls itselfcoreclaw-mcp-server
- Server version71f72b2
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 21 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Once connected
- create_worker_task, update_worker_task, update_worker_task_input, delete_worker_task change data without a sign-in: anyone with the address can call them.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer175 ms
- Space in an agent's context≈ 12,792 tokensthe definitions of all its tools (42), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 42 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
Worth a look
- Tools that change data, on a server that answers without a sign-in: create_worker_task, update_worker_task, update_worker_task_input, delete_worker_task
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
list_proxy_regionsList CoreClaw proxy regions in English or Chinese. WHEN TO USE: Use when the user needs proxy country or region codes before running a worker, such as US, JP, DE, or Chinese localized names. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应…
list_store_workersSearch the public CoreClaw worker marketplace for ready-to-run workers. WHEN TO USE: Use when the user wants to find, discover, browse, or search CoreClaw scrapers/workers by keyword or site name. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应…
list_workersList CoreClaw workers owned by the current user. WHEN TO USE: Use when the user wants their private/current-user workers, not the public marketplace. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not…
get_workerGet detail for a CoreClaw worker. WHEN TO USE: Use before running a worker to inspect version, README, and parameters. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use public web search or code…
get_worker_input_schemaGet the public input JSON schema for a CoreClaw worker. WHEN TO USE: Use when the user wants to know required input fields or before composing run_worker input_json. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN…
list_worker_tasksList saved CoreClaw worker tasks for the current user. WHEN TO USE: Use when the user wants saved tasks, scheduled presets, configured jobs, or task ids. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do…
get_worker_taskGet detail for a specific saved CoreClaw worker task. WHEN TO USE: Use when the user wants to inspect a saved task's configuration, schedule, or input. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do…
get_worker_task_inputGet the input payload for a saved CoreClaw worker task. WHEN TO USE: Use when the user wants to inspect or copy a task's saved input parameters. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use…
get_account_infoGet the current user's CoreClaw account balance and traffic quota. WHEN TO USE: Use when the user asks for balance, remaining traffic, quota, billing state, or whether they can run jobs. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应…
create_worker_taskCreate a new saved CoreClaw worker task with input and optional schedule. WHEN TO USE: Use when the user wants to save a worker configuration as a reusable, scheduled task. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。…
update_worker_taskUpdate a saved CoreClaw worker task's metadata and schedule. Partial update: omit fields to keep their current values. WHEN TO USE: Use when the user wants to change a task's title, description, or schedule settings. 中文触发: 当用户要在 CoreClaw…
update_worker_task_inputUpdate the input payload for a saved CoreClaw worker task. WHEN TO USE: Use when the user wants to change a task's saved input parameters without modifying its title/schedule. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task…
run_workerRun a CoreClaw worker with an ad-hoc JSON input payload. WHEN TO USE: Use when the user wants to start, execute, scrape, crawl, or run a worker with specific input. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT…
run_worker_taskRun a saved CoreClaw worker task. WHEN TO USE: Use when the user wants to execute a configured task rather than supply ad-hoc worker input. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use…
run_workers_batchRun multiple CoreClaw workers in one call and return a per-item summary (run_slug, status, verdict). Serial by default; optional concurrency. WHEN TO USE: Use when accepting/validating many workers at once (e.g. full-store smoke test) to…
queue_worker_runSubmit a CoreClaw worker run to the Run Queue instead of executing immediately. WHEN TO USE: Use when the user wants to queue a run for later activation rather than start it right away. Returns a queue_ref to track, activate, or release…
list_run_queue_itemsList items in the CoreClaw Run Queue. WHEN TO USE: Use when the user wants to inspect queued runs, find a queue_ref, or check waiting/inactive items before activating or releasing. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task…
activate_run_queue_itemsActivate one or more waiting CoreClaw Run Queue items so they start executing. WHEN TO USE: Use when the user previously queued runs via queue_worker_run and now wants to start them. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应…
release_run_queue_itemsRelease (remove) one or more CoreClaw Run Queue items so they never execute. WHEN TO USE: Use when the user no longer needs queued runs and wants to remove them in bulk. This is the batch version. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应…
release_run_queue_itemRelease (remove) a single CoreClaw Run Queue item so it never executes. WHEN TO USE: Use when the user wants to remove one queued run by its queue_id. Same as release_run_queue_items but takes the queue_ref in the path. 中文触发: 当用户要在…
list_worker_runsList the current user's CoreClaw worker runs. WHEN TO USE: Use when the user wants run history, recent jobs, or to find a run_id by worker or status. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not…
get_last_worker_runGet the current user's most recent CoreClaw worker run. WHEN TO USE: Use when the user says last run, latest job, most recent scrape, or asks what just happened. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO…
get_worker_runGet detail for a specific CoreClaw worker run by run_id. WHEN TO USE: Use when the user gives a run id or wants status/cost/detail for a specific run. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do…
poll_runPoll a CoreClaw worker run until it reaches a terminal state (succeeded/failed/aborted) or the timeout elapses, then return the final status and optionally a result preview. WHEN TO USE: Use when run_worker returned an async run and the…
verify_runVerify a CoreClaw worker run produced real, usable data and return a structured PASS/NO_DATA/FAILED/ERROR_RECORD verdict. WHEN TO USE: Use after a run reaches a terminal state to get an acceptance verdict without manually inspecting…
get_worker_last_runGet the most recent run for a specific CoreClaw worker. WHEN TO USE: Use when the user asks for the last run of a specific worker. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use public web…
list_last_worker_run_resultsList paginated results from the current user's most recent CoreClaw run. WHEN TO USE: Use when the user wants to preview, inspect, or page through latest run output. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN…
export_last_worker_run_resultsExport the current user's most recent CoreClaw run results. WHEN TO USE: Use when the user asks to download/export the latest run as CSV or JSON. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use…
get_last_worker_run_logGet logs for the current user's most recent CoreClaw worker run. WHEN TO USE: Use when debugging why the latest run failed, stalled, or produced unexpected output. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT…
list_worker_run_resultsList paginated results for a specific CoreClaw worker run. WHEN TO USE: Use when the user wants records/output rows from a known run id. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use public…
export_worker_run_resultsExport result data for a specific CoreClaw worker run. WHEN TO USE: Use when the user asks to download or save output from a known run as CSV or JSON. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do…
get_worker_run_logGet logs for a specific CoreClaw worker run, optionally filtered to lines matching error/traceback keywords. WHEN TO USE: Use to debug a known run id, especially failed, stalled, or suspicious runs. Pass grep to extract only…
list_worker_last_run_resultsList paginated results from the most recent run of a specific CoreClaw worker. WHEN TO USE: Use when the user wants latest output rows for a known worker. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE…
export_worker_last_run_resultsExport results from the most recent run of a specific CoreClaw worker. WHEN TO USE: Use when the user asks to download/export the latest output for a known worker. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT…
get_worker_last_run_logGet logs for the most recent run of a specific CoreClaw worker. WHEN TO USE: Use when debugging the latest run for a specific worker. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use public web…
rerun_last_worker_runRerun the current user's most recent CoreClaw worker run with the same saved inputs. WHEN TO USE: Use when the user says rerun last, retry latest, or do the previous scrape again. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task…
rerun_worker_runRerun a specific CoreClaw worker run with the same saved inputs. WHEN TO USE: Use when the user wants to retry or repeat a known run id. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use public…
rerun_worker_last_runRerun the most recent run for a specific CoreClaw worker. WHEN TO USE: Use when the user asks to retry or repeat the latest run for a known worker. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not…
abort_last_worker_runAbort the current user's most recent CoreClaw worker run. WHEN TO USE: Use when the user wants to stop or cancel the last running job. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use public web…
abort_worker_runAbort a specific CoreClaw worker run by run_id. WHEN TO USE: Use when the user wants to cancel a known running run. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use public web search or code…
abort_worker_last_runAbort the most recent run for a specific CoreClaw worker. WHEN TO USE: Use when the user wants to cancel the latest active run of a known worker. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use…
delete_worker_taskDelete a saved CoreClaw worker task. WHEN TO USE: Use when the user wants to permanently remove a saved task. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use public web search or code search…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"coreclaw": {
"type": "http",
"url": "https://mcp.coreclaw.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http coreclaw https://mcp.coreclaw.com/mcpclaude.ai, ChatGPT and other clients: add https://mcp.coreclaw.com/mcp as a custom connector in the settings.
OpenAPI spec
35 paths, read 2026-10-09. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.