{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_nqmp6gd6zpek","handle":"voidcrawl-mcp","url":"https://wellknown.network/agents/voidcrawl-mcp","links":{"self":"https://wellknown.network/agents/voidcrawl-mcp/record.json","html":"https://wellknown.network/agents/voidcrawl-mcp","markdown":"https://wellknown.network/agents/voidcrawl-mcp/record.md","api":"https://wellknown.network/api/v1/agents/voidcrawl-mcp","status":"https://wellknown.network/api/v1/agents/voidcrawl-mcp/status","claim":"https://wellknown.network/agents/voidcrawl-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/voidcrawl-mcp/claim.json","badge":"https://wellknown.network/agents/voidcrawl-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:voidcrawl-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"voidcrawl-mcp","summary":"Stdio MCP server for stealthy headless Chrome via voidcrawl — expose the voidcrawl Chrome pool to Claude Code","description":"# voidcrawl-mcp\n\nRust-native MCP server that exposes [`void_crawl_core`](../core)'s\nstealth-patched Chrome pool to Claude Code. Headless by default,\nconcurrent by construction — ten tabs in parallel is the norm.\n\n## Why not claude-in-chrome?\n\n- `claude-in-chrome` drives the user's single visible Chrome tab.\n- `voidcrawl-mcp` drives a headless pool with real concurrency and\n  per-session isolation. Pick it for bulk scraping, bot-detection\n  targets, and subagent fan-out. See [`../../.claude/skills/voidcrawl/SKILL.md`](../../.claude/skills/voidcrawl/SKILL.md) for the full decision rubric.\n\n## Tools\n\n| Tool              | Kind      | Summary                                                     |\n| ----------------- | --------- | ----------------------------------------------------------- |\n| `fetch`           | stateless | Single URL → `{ html, title, status_code, ... }`.           |\n| `fetch_many`      | stateless | N URLs in parallel; pool semaphore caps concurrency.        |\n| `screenshot`      | stateless | Full-page PNG as `image/png` content.                       |\n| `session_open`    | stateful  | Launches a dedicated Chrome, returns `session_id`.          |\n| `session_navigate`| stateful  | Goto URL within a session and wait for settle.              |\n| `session_content` | stateful  | HTML + title + URL of the session's current page.           |\n| `session_screenshot` | stateful | PNG of the session's current page as-is — no navigation. |\n| `session_close`   | stateful  | Shut down the session's Chrome.                             |\n| `pool_status`     | diag      | Pool config + live session count.                           |\n| `download`        | stateless | Download a file by URL through stealth Chrome and scan it with the built-in antivirus gate. **Opt-in** (`VOIDCRAWL_ALLOW_DOWNLOADS=1`). |\n| `download_arm` / `download_wait` | stateful | Capture a download started by a page action (button with no stable URL), then scan it. **Opt-in** (`VOIDCRAWL_ALLOW_DOW…","publisher":{"name":"Cascading Labs","url":null},"homepage":"https://github.com/CascadingLabs/VoidCrawl","repository":"https://github.com/CascadingLabs/VoidCrawl/blob/main/CHANGELOG.md","version":"0.5.0","license":"Apache-2.0","protocols":["mcp"],"tags":["mcp","chrome","cdp","browser","automation","claude-code"],"pricing":null,"endpoints":[{"url":"pypi:voidcrawl-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"infra.browser-automation","name":"Browser Automation","confidence":1,"provenance":"declared"},{"slug":"data.web-scraping","name":"Web Scraping","confidence":0.791,"provenance":"derived"}],"categories":["data","infra"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"voidcrawl-mcp","registry":"pypi","observedAt":"2026-09-10T15:25:17.116Z","publishedAt":"2026-08-16T13:49:33.861049Z","latestVersion":"0.5.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"voidcrawl-mcp","url":"https://pypi.org/project/voidcrawl-mcp/","firstSeenAt":"2026-09-10T15:23:52.971Z","fetchedAt":"2026-09-10T15:23:52.971Z","normalizedAt":"2026-09-10T15:23:52.971Z"}]},"firstSeenAt":"2026-09-10T15:23:52.971Z","updatedAt":"2026-09-10T15:25:17.116Z"}