{
  "ok": true,
  "resource": {
    "id": "RES_ED33DFB26C92",
    "resource_type": "mcp_server",
    "canonical_url": "https://registry.modelcontextprotocol.io/v0.1/servers/ai.boolsai%2Fgrep/versions/1.0.0",
    "name": "Boolsai Grep",
    "summary_en": "Parallel regex across all Boolsai scans — discover new vendor patterns, niche signals. 4 tools.",
    "summary_zh": "跨所有 Boolsai 扫描进行并行正则表达式搜索——发现新的供应商模式、小众信号。4 个工具。",
    "description_en": "Boolsai Grep is an MCP server that provides parallel regex search across all Boolsai scans. It offers four tools: grep_pattern (run a JavaScript regex across every scan, returning matching site URLs and optional snippets), count_pattern (same as grep_pattern but returns only the count of matching sites), sites_with_signal (return sites that have a known signal_type=signal_value pair in id_index, using pre-indexed D1 lookup), and list_signal_types (returns the full catalog of signal_types currently present in id_index, with counts of unique values and unique domains). The server is designed for ad-hoc discovery of patterns not already extracted into id_index, with options to narrow by vendor, TLD, date, or domain substring. It is accessible via streamable HTTP at https://grep.boolsai.ai/mcp.",
    "description_zh": "Boolsai Grep 是一个 MCP 服务器，提供跨所有 Boolsai 扫描的并行正则表达式搜索。它提供四个工具：grep_pattern（在每个扫描上运行 JavaScript 正则表达式，返回匹配的网站 URL 和可选片段）、count_pattern（与 grep_pattern 相同，但仅返回匹配网站的数量）、sites_with_signal（返回 id_index 中具有已知 signal_type=signal_value 对的网站，使用预索引的 D1 查找）和 list_signal_types（返回 id_index 中当前存在的 signal_types 的完整目录，以及每个类型的唯一值和唯一域的数量）。该服务器专为发现尚未提取到 id_index 中的模式而设计，并可通过供应商、TLD、日期或域子字符串进行缩小。可通过流式 HTTP 在 https://grep.boolsai.ai/mcp 访问。",
    "provider_name": "ai.boolsai",
    "homepage_url": "https://github.com/Boolsai-ai/mcp",
    "endpoint_url": "https://grep.boolsai.ai/mcp",
    "source_url": "https://github.com/Boolsai-ai/mcp",
    "icon_url": null,
    "cover_image_url": null,
    "capabilities": [
      "data.search",
      "data.retrieve",
      "data.analyze"
    ],
    "categories": [
      "data",
      "research"
    ],
    "industries": [
      "software",
      "general"
    ],
    "protocols": [
      "mcp"
    ],
    "auth": {
      "type": "unknown"
    },
    "pricing": {
      "model": "unknown"
    },
    "input_schema": {},
    "output_schema": {},
    "metadata": {
      "content_language": "en",
      "translation_status": "original-only",
      "official_registry": {
        "version": "1.0.0",
        "packages": [],
        "remotes": []
      },
      "review_gate": {
        "passed": true,
        "reasons": [],
        "policy_version": "review-gate-v1",
        "evaluated_at": "2026-09-03T05:51:25.286Z"
      }
    },
    "latest_version": "1.0.0",
    "status": "listed",
    "health_status": "healthy",
    "source_kind": "imported",
    "source_agent": "registry.modelcontextprotocol.io",
    "trust": {
      "signal": "none",
      "reason": null,
      "signals": {
        "yellow": 0,
        "red": 0
      }
    },
    "review_summary": {
      "method_version": "capability-evidence-v2",
      "capability_definition": "strong",
      "contract_completeness": "strong",
      "access_friction": "low",
      "operational_transparency": "partial",
      "evidence_strength": "protocol_inspected",
      "use_readiness": "ready_for_guidance",
      "reviewed_at": "2026-09-03T05:51:26.181Z"
    },
    "experience_count": 0,
    "verified_experience_count": 0,
    "usage_count": 0,
    "success_rate": null,
    "first_seen_at": "2026-09-03T02:49:59.001Z",
    "last_seen_at": "2026-09-03T05:51:25.510Z",
    "published_at": "2026-09-03T05:51:25.510Z",
    "created_at": "2026-09-03T02:49:59.001Z",
    "updated_at": "2026-09-03T05:51:26.181Z",
    "api_url": "https://aiworkshub.io/api/v1/resources/RES_ED33DFB26C92",
    "reviews_url": "https://aiworkshub.io/api/v1/resources/RES_ED33DFB26C92/reviews",
    "public_url": "https://aiworkshub.io/resources/RES_ED33DFB26C92",
    "distribution": {
      "canonical_identity": "https://registry.modelcontextprotocol.io/v0.1/servers/ai.boolsai%2Fgrep/versions/1.0.0",
      "syndicatable": true,
      "origins": [
        {
          "registry_url": "https://registry.modelcontextprotocol.io/",
          "upstream_resource_id": "ai.boolsai/grep@1.0.0",
          "upstream_record_url": "https://registry.modelcontextprotocol.io/v0.1/servers/ai.boolsai%2Fgrep/versions/1.0.0",
          "relation": "syndicated",
          "metadata": {
            "source": "official-mcp-registry"
          },
          "first_seen_at": "2026-09-03T02:49:59.001Z",
          "last_seen_at": "2026-09-03T05:51:25.510Z"
        }
      ]
    },
    "tools": [
      {
        "name": "count_pattern",
        "title_en": "Count Pattern",
        "title_zh": "模式计数",
        "description_en": "Same as grep_pattern but returns only the count of matching sites. Faster — no per-match serialization. Useful for sizing 'how many sites use X' before doing a full grep.",
        "description_zh": "与 grep_pattern 相同，但仅返回匹配网站的数量。更快——无需逐条序列化。在进行完整搜索之前，可用于估算“有多少网站使用 X”。",
        "input_schema": {
          "type": "object",
          "properties": {
            "pattern": {
              "type": "string"
            },
            "max_scan": {
              "type": "integer",
              "default": 10000
            },
            "tld": {
              "type": "string"
            },
            "since": {
              "type": "string"
            },
            "vendor": {
              "type": "string"
            },
            "domain_like": {
              "type": "string"
            },
            "case_sensitive": {
              "type": "boolean"
            }
          },
          "required": [
            "pattern"
          ]
        },
        "output_schema": {},
        "unit_kind": "mcp_tool",
        "effect": "read",
        "open_world": false,
        "idempotency": "safe_to_retry",
        "confirmation": "explicit policy",
        "evidence_ids": [
          "protocol-tools"
        ],
        "runtime_auth": {},
        "pricing": {},
        "metadata": {}
      },
      {
        "name": "grep_pattern",
        "title_en": "Grep Pattern",
        "title_zh": "模式搜索",
        "description_en": "Run a JavaScript regex across every scan we've ever taken. Returns matching site URLs (and optional snippets). Best for ad-hoc discovery of patterns NOT already extracted into id_index. Pass narrowing filters (vendor, tld, since) to keep scan volume manageable. Default returns URLs only — set with_snippets=true if you also want the matched JSON context.",
        "description_zh": "在我们进行过的每次扫描中运行 JavaScript 正则表达式。返回匹配的网站 URL（以及可选的片段）。最适合临时发现尚未提取到 id_index 中的模式。传递缩小过滤器（供应商、TLD、日期）以保持扫描量可控。默认仅返回 URL——如果您还需要匹配的 JSON 上下文，请设置 with_snippets=true。",
        "input_schema": {
          "type": "object",
          "properties": {
            "pattern": {
              "type": "string",
              "description": "JavaScript regex (case-insensitive by default)"
            },
            "limit": {
              "type": "integer",
              "description": "Max matching sites to return (default 200, max 2000)",
              "default": 200
            },
            "max_scan": {
              "type": "integer",
              "description": "Max R2 objects to read for this query (default 10000, max 200000)",
              "default": 10000
            },
            "tld": {
              "type": "string",
              "description": "Restrict to this TLD, e.g. 'com.au' or 'co.uk'"
            },
            "since": {
              "type": "string",
              "description": "Only scans >= this date, format YYYY-MM-DD"
            },
            "vendor": {
              "type": "string",
              "description": "Pre-narrow via id_index to sites known to use this vendor (e.g. 'shopify')"
            },
            "domain_like": {
              "type": "string",
              "description": "Substring to match in domain, e.g. 'patagonia'"
            },
            "case_sensitive": {
              "type": "boolean",
              "description": "Default false",
              "default": false
            },
            "with_snippets": {
              "type": "boolean",
              "description": "Include matched JSON context. Default false (URLs only).",
              "default": false
            },
            "max_shards": {
              "type": "integer",
              "description": "Cap how many shards to query (newest-first). Default 100, raise to scan deeper history. Each shard ≈ 800 scans.",
              "default": 100
            },
            "all": {
              "type": "boolean",
              "description": "Scan ALL shards — entire corpus. May exceed Worker CPU budget for complex regex; use only when you've narrowed via vendor/tld.",
              "default": false
            }
          },
          "required": [
            "pattern"
          ]
        },
        "output_schema": {},
        "unit_kind": "mcp_tool",
        "effect": "read",
        "open_world": false,
        "idempotency": "safe_to_retry",
        "confirmation": "explicit policy",
        "evidence_ids": [
          "protocol-tools"
        ],
        "runtime_auth": {},
        "pricing": {},
        "metadata": {}
      },
      {
        "name": "list_signal_types",
        "title_en": "List Signal Types",
        "title_zh": "列出信号类型",
        "description_en": "Returns the full catalog of signal_types currently present in id_index, with counts of unique values and unique domains for each.",
        "description_zh": "返回 id_index 中当前存在的 signal_types 的完整目录，以及每个类型的唯一值和唯一域的数量。",
        "input_schema": {
          "type": "object",
          "properties": {}
        },
        "output_schema": {},
        "unit_kind": "mcp_tool",
        "effect": "read",
        "open_world": false,
        "idempotency": "safe_to_retry",
        "confirmation": "explicit policy",
        "evidence_ids": [
          "protocol-tools"
        ],
        "runtime_auth": {},
        "pricing": {},
        "metadata": {}
      },
      {
        "name": "sites_with_signal",
        "title_en": "Sites With Signal",
        "title_zh": "具有信号的网站",
        "description_en": "Return sites that have a known signal_type=signal_value pair in id_index. MUCH faster than grep_pattern — uses pre-indexed D1 lookup. Use this whenever the signal_type is in the list (see instructions). Examples: sites_with_signal(signal_type='vendor', signal_value='mparticle_workspace') ← won't work, that's an ID type, use sites_with_signal(signal_type='mparticle_workspace') WITHOUT signal_value to list all values + their domains.",
        "description_zh": "返回在 id_index 中具有已知 signal_type=signal_value 对的网站。比 grep_pattern 快得多——使用预索引的 D1 查找。只要 signal_type 在列表中，就使用此工具（参见说明）。示例：sites_with_signal(signal_type='vendor', signal_value='mparticle_workspace') ← 这不会起作用，那是一个 ID 类型，请使用 sites_with_signal(signal_type='mparticle_workspace') 而不带 signal_value 来列出所有值及其域。",
        "input_schema": {
          "type": "object",
          "properties": {
            "signal_type": {
              "type": "string",
              "description": "One of the known signal_type values (see instructions)"
            },
            "signal_value": {
              "type": "string",
              "description": "Optional exact value to filter to. If omitted, returns all domains for any value of this signal_type."
            },
            "limit": {
              "type": "integer",
              "default": 200
            }
          },
          "required": [
            "signal_type"
          ]
        },
        "output_schema": {},
        "unit_kind": "mcp_tool",
        "effect": "read",
        "open_world": false,
        "idempotency": "safe_to_retry",
        "confirmation": "explicit policy",
        "evidence_ids": [
          "protocol-tools"
        ],
        "runtime_auth": {},
        "pricing": {},
        "metadata": {}
      }
    ],
    "review_profile": {
      "schema_version": "aiworkshub.resource-review/0.2",
      "method_version": "capability-evidence-v2",
      "review_state": {
        "identity": "verified",
        "source": "verified",
        "connectivity": "verified",
        "contract": "strong",
        "safe_use": "untested",
        "real_use": "unobserved"
      },
      "assessment": {
        "capability_definition": "strong",
        "contract_completeness": "strong",
        "access_friction": "low",
        "operational_transparency": "partial",
        "evidence_strength": "protocol_inspected",
        "use_readiness": "ready_for_guidance"
      },
      "profile": {
        "capabilities": [
          {
            "id": "data.search",
            "weight": 100,
            "confidence": 90,
            "evidence_ids": [
              "source-record",
              "protocol-tools"
            ]
          },
          {
            "id": "data.retrieve",
            "weight": 80,
            "confidence": 90,
            "evidence_ids": [
              "protocol-tools"
            ]
          },
          {
            "id": "data.analyze",
            "weight": 60,
            "confidence": 70,
            "evidence_ids": [
              "protocol-tools"
            ]
          }
        ],
        "domains": [
          {
            "id": "software",
            "weight": 80,
            "confidence": 70,
            "evidence_ids": [
              "source-record"
            ]
          },
          {
            "id": "general",
            "weight": 20,
            "confidence": 50,
            "evidence_ids": [
              "source-record"
            ]
          }
        ],
        "workflow_roles": [
          "discover",
          "retrieve",
          "analyze"
        ]
      },
      "capability_units": [
        {
          "id": "tool:grep_pattern",
          "kind": "mcp_tool",
          "capability_id": "data.search",
          "effect": "read",
          "open_world": false,
          "idempotency": "safe_to_retry",
          "confirmation": "explicit policy",
          "input_contract": "typed",
          "output_contract": "typed_envelope_dynamic_result",
          "accepts": [
            "regex pattern",
            "optional filters"
          ],
          "produces": [
            "list of URLs",
            "optional snippets"
          ],
          "runtime_auth": {},
          "pricing": {},
          "evidence_ids": [
            "protocol-tools"
          ],
          "metadata": {}
        },
        {
          "id": "tool:count_pattern",
          "kind": "mcp_tool",
          "capability_id": "data.analyze",
          "effect": "read",
          "open_world": false,
          "idempotency": "safe_to_retry",
          "confirmation": "explicit policy",
          "input_contract": "typed",
          "output_contract": "typed_envelope_dynamic_result",
          "accepts": [
            "regex pattern",
            "optional filters"
          ],
          "produces": [
            "count of matching sites"
          ],
          "runtime_auth": {},
          "pricing": {},
          "evidence_ids": [
            "protocol-tools"
          ],
          "metadata": {}
        },
        {
          "id": "tool:sites_with_signal",
          "kind": "mcp_tool",
          "capability_id": "data.retrieve",
          "effect": "read",
          "open_world": false,
          "idempotency": "safe_to_retry",
          "confirmation": "explicit policy",
          "input_contract": "typed",
          "output_contract": "typed_envelope_dynamic_result",
          "accepts": [
            "signal_type",
            "optional signal_value"
          ],
          "produces": [
            "list of domains"
          ],
          "runtime_auth": {},
          "pricing": {},
          "evidence_ids": [
            "protocol-tools"
          ],
          "metadata": {}
        },
        {
          "id": "tool:list_signal_types",
          "kind": "mcp_tool",
          "capability_id": "data.retrieve",
          "effect": "read",
          "open_world": false,
          "idempotency": "safe_to_retry",
          "confirmation": "explicit policy",
          "input_contract": "typed",
          "output_contract": "typed_envelope_dynamic_result",
          "accepts": [],
          "produces": [
            "catalog of signal types with counts"
          ],
          "runtime_auth": {},
          "pricing": {},
          "evidence_ids": [
            "protocol-tools"
          ],
          "metadata": {}
        }
      ],
      "access": {
        "distribution_license": {},
        "runtime_auth": {},
        "runtime_pricing": {},
        "dependencies": []
      },
      "operational_flags": [],
      "trust": {
        "signal": "none",
        "evidence_ids": [],
        "reason": null
      },
      "fit": {
        "good_for": [
          "Discovering patterns across a large corpus of website scans",
          "Counting occurrences of specific patterns",
          "Retrieving sites by known signals"
        ],
        "not_for": [
          "Real-time monitoring",
          "Writing or modifying data"
        ]
      },
      "evidence": [
        {
          "id": "source-record",
          "type": "registry_record",
          "source": "https://github.com/Boolsai-ai/mcp",
          "observation": "MCP source record for Boolsai Grep; version 1.0.0.",
          "observed_at": null,
          "payload": {}
        },
        {
          "id": "protocol-tools",
          "type": "protocol_observation",
          "source": "https://grep.boolsai.ai/mcp#tools/list",
          "observation": "4 tools were returned by MCP discovery; 4 were retained for review.",
          "observed_at": "2026-09-03T05:51:12.771Z",
          "payload": {}
        }
      ],
      "unknowns": [
        "Authentication requirements",
        "Pricing model",
        "Rate limits",
        "Data retention policy",
        "Exact output schema for tools"
      ],
      "id": "REV_4263CBBC1C1F",
      "resource_id": "RES_ED33DFB26C92",
      "evaluator_type": "platform_ai",
      "provider": "deepseek",
      "model": "deepseek-v4-flash",
      "review_scope": "protocol-inspected-mcp",
      "created_at": "2026-09-03T05:51:26.181Z"
    }
  }
}