{ "$schema": "https://readbeforerun.ai/schema/entry.schema.json", "entry": { "id": "google-secops-mcp", "name": "Google Security Operations MCP Server", "summary": "MCP server for Google Security Operations (Chronicle) with 68 tools for event search, alerts, detection rules, log ingestion and SIEM configuration.", "draft": "review", "type": "mcp-server", "mission": [ "defensive" ], "task": [ "alert-triage", "detection-engineering" ], "domain": [ "security-operations" ], "runtime": [ "mcp-generic", "claude-code", "gemini-cli", "cursor" ], "tier": "listed", "last_checked": "2026-10-21", "next_check": "2027-01-19", "freshness": "fresh", "superseded": false, "in_my_kit": null, "advice": null, "code_shows": "reads credential stores · changes config or installs globally · Approval: unknown", "source": { "repo": "https://github.com/google/mcp-security", "subpath": "server/secops", "commit": "ceb703aee136d4ce0b23213bca938133212274b9", "version": "secops-v0.7.1", "license": "Apache-2.0" }, "install": { "skills_cli": null, "claude_code": null, "upstream": "uvx --from google-secops-mcp secops_mcp", "bundled": false }, "scan": { "status": "static scan pending (not run)" }, "reach": { "method": "reach-v0.1", "level": 3, "level_source": "static", "level_label": "privileged", "unknown_axes": 1, "verdict": "not-run", "badge": "reach 3 · not run yet", "long": "reach 3 from code (privileged); lab: not run yet", "declared": { "fs": 1, "net": 1, "cred": 3, "persist": 2, "hitl": 1 }, "static": { "level": 3, "fs": 1, "net": 1, "exec": 0, "cred": 3, "persist": 2, "hitl": null, "unknown": [ "hitl" ] }, "observed": null, "surplus": null, "fit": null, "exports": { "aivss": { "fs": 0.5, "net": 0.5, "exec": 0, "cred": 1, "persist": 0.5, "hitl": null }, "usf_risk_tier": "L3" } }, "profile": { "read_at": "ceb703aee136d4ce0b23213bca938133212274b9", "read_on": "2026-10-25", "overview": "An MCP server that connects MCP clients to Google's Chronicle Security Operations suite, with tools for event search, alerts, detection rules, log ingestion and SIEM configuration.", "purpose": [ "Gives MCP clients access to Google Security Operations (Chronicle) for threat detection, investigation and hunting.", "Performs security operations tasks in Chronicle, including natural-language event search.", "Gets data into Chronicle through raw log and UDM event ingestion, custom parsers and feed configuration." ], "use_cases": [ { "text": "Retrieve and monitor security alerts from Chronicle.", "task": "alert-triage" }, { "text": "Run detection rules against historical data as retrohunts and track their results.", "task": "detection-engineering" }, { "text": "Look up IPs, domains, hashes and other indicators against Chronicle log history.", "task": "threat-intel-enrichment" }, { "text": "Create and deploy rule exclusions to filter false positives and tune detection rules.", "task": "detection-engineering" } ], "maturity": null, "capabilities": [ { "name": "Security Tools", "effects": [ "reads", "changes" ], "enabled": "default" }, { "name": "Log Ingestion Tools", "effects": [ "reads", "changes" ], "enabled": "default" }, { "name": "Parser Management Tools", "effects": [ "reads", "changes" ], "enabled": "default" }, { "name": "Data Table Management Tools", "effects": [ "reads", "changes", "deletes" ], "enabled": "default" }, { "name": "Reference List Management Tools", "effects": [ "reads", "changes" ], "enabled": "default" }, { "name": "Feed Management Tools", "effects": [ "reads", "changes", "deletes" ], "enabled": "default" }, { "name": "Curated Rules Management Tools", "effects": [ "reads", "changes" ], "enabled": "default" }, { "name": "Rule Exclusions Management Tools", "effects": [ "reads", "changes" ], "enabled": "default" }, { "name": "Watchlist Management Tools", "effects": [ "reads", "changes", "deletes" ], "enabled": "default" }, { "name": "Investigation Management Tools", "effects": [ "reads", "changes" ], "enabled": "default" } ], "effects": [ "reads", "changes", "deletes" ], "runs": "local-process", "listens": [], "sends_to": [ { "to": "Google SecOps Chronicle API", "kind": "vendor-api", "when": "always" }, { "to": "Gemini in Chronicle", "kind": "vendor-api", "when": "optional" }, { "to": "Chronicle natural-language translation", "kind": "vendor-api", "when": "optional" } ], "model": "client", "needs": [ { "kind": "account", "text": "A Google Security Operations (Chronicle) instance, identified by Google Cloud project ID, Chronicle customer ID and region." }, { "kind": "credentials", "text": "Google Cloud Application Default Credentials by default, set up with gcloud auth application-default login." }, { "kind": "credentials", "text": "Optionally a service account JSON key file, whose path is read from SECOPS_SA_PATH." }, { "kind": "runtime", "text": "Python 3.11 or later." }, { "kind": "tools", "text": "uv (recommended by the author) or pip to install and run the package." }, { "kind": "tools", "text": "The gcloud CLI to create Application Default Credentials." }, { "kind": "authorization", "text": "Chronicle API access for the identity in use, listed as a requirement for the integration tests." }, { "kind": "setting", "text": "CHRONICLE_PROJECT_ID, CHRONICLE_CUSTOMER_ID, CHRONICLE_REGION and SECOPS_SA_PATH are passed through the env block of the MCP client configuration." } ] }, "urls": { "page": "/catalog/google-secops-mcp/", "json": "/entries/google-secops-mcp.json", "md": "/catalog/google-secops-mcp.md", "badge": "/badge/google-secops-mcp.svg" } }, "data": { "schema_version": "0.5", "slug": "google-secops-mcp", "name": "Google Security Operations MCP Server", "summary": "MCP server for Google Security Operations (Chronicle) with 68 tools for event search, alerts, detection rules, log ingestion and SIEM configuration.", "draft": "review", "in_my_kit": null, "type": "mcp-server", "mission": [ "defensive" ], "task": [ "alert-triage", "detection-engineering" ], "domain": [ "security-operations" ], "phase": [ "def:detect", "def:respond" ], "role": [ "soc" ], "runtime": [ "mcp-generic", "claude-code", "gemini-cli", "cursor" ], "auth": "oauth2", "autonomy": null, "addresses": [], "frameworks": { "owasp_ast": [], "owasp_asi": [], "attack_tactic": [], "atlas": [] }, "source": { "repo": "https://github.com/google/mcp-security", "subpath": "server/secops", "commit": "ceb703aee136d4ce0b23213bca938133212274b9", "version": "secops-v0.7.1", "license": "Apache-2.0", "manifest": "pyproject.toml", "also_listed": {} }, "upstream": { "checked_at": "2026-10-21", "updated_at": "2026-10-16", "current_release": "secops-v0.7.1", "archived": false, "stars": 535, "commit_history": {}, "releases_since_pin": 0 }, "install": { "upstream": "uvx --from google-secops-mcp secops_mcp", "upstream_evidence": "README.md#L69", "bundled": false }, "scan": [ { "tool": "cisco-skill-scanner", "version": "not-run", "llm_judge": false, "date": "2026-10-21", "result": "pending" } ], "privileges": { "method": "reach-v0.1", "declared": { "axes": { "fs": 1, "net": 1, "cred": 3, "persist": 2, "hitl": 1 }, "evidence": { "fs": "server/secops/README.md#L392-393 the author lets the server read a service-account key file from a path the user sets", "net": "server/secops/README.md#L3-4 the author names Google Security Operations as the only service the server talks to", "cred": "server/secops/README.md#L383-387 the author makes Google Cloud Application Default Credentials the default, which is the user's cloud credential profile outside the working directory", "persist": "server/secops/README.md#L222-228 the author lists tools that create, update, enable, disable and delete feeds, parsers, data tables, reference lists, rule exclusions and watchlists", "hitl": "server/secops/README.md#L333-340 the documented pip client configuration pre-approves three read tools" } }, "static": { "level": 3, "axes": { "fs": 1, "net": 1, "exec": 0, "cred": 3, "persist": 2, "hitl": null }, "evidence": { "fs": "server/secops/secops_mcp/server.py#L71-73 the server passes a key-file path from SECOPS_SA_PATH to the SDK, which reads it from any location, and writes no local files", "net": "server/secops/secops_mcp/server.py#L77-79 all tools reach the network only through the SecOps SDK client for the configured or per-call project, customer and region, and the server runs over stdio only", "exec": "none found: patterns exec-v0.1 in 24 files at ceb703a", "cred": "server/secops/secops_mcp/server.py#L74-75 without SECOPS_SA_PATH the client is created without explicit credentials and falls back to Application Default Credentials, the user's Google Cloud credential profile", "persist": "server/secops/secops_mcp/tools/curated_rules_management.py#L701 one of 27 tools that change SecOps configuration or data with a direct SDK call and no confirmation step", "hitl": "no evidence: no approval settings were found in the code, but the search patterns for approvals match several lines, so a zero cannot be written" }, "unknown": [ "hitl" ] }, "min_config": { "status": "derived", "note": "derived from the code, not tested in the lab; use a dedicated service account with read-only SecOps roles through SECOPS_SA_PATH instead of personal Application Default Credentials, set project, customer and region explicitly because built-in fallback IDs apply otherwise, keep the service account limited to one instance because any call can name another project, and pin google-secops-mcp==0.7.1" }, "override": null, "reviews": [] }, "status": { "tier": "listed", "last_checked": "2026-10-21", "next_check": "2027-01-19", "freshness": "fresh", "superseded": false, "superseded_by": null, "added": "2026-10-21", "added_by": "scout" }, "evidence": { "runs": [], "badge": "/badge/google-secops-mcp.svg" }, "changes": [] }, "profile": { "schema_version": "0.1", "entry": "google-secops-mcp", "draft": "review", "commit": "ceb703aee136d4ce0b23213bca938133212274b9", "read_on": "2026-10-25", "check": { "date": "2026-10-25", "facts": 57, "confirmed": 57, "verified": 50 }, "overview": { "text": "An MCP server that connects MCP clients to Google's Chronicle Security Operations suite, with tools for event search, alerts, detection rules, log ingestion and SIEM configuration.", "ev": "server/secops/README.md#L3-4 author's own description of the server" }, "purpose": [ { "text": "Gives MCP clients access to Google Security Operations (Chronicle) for threat detection, investigation and hunting.", "ev": "README.md#L6 repository README states what the Chronicle server is for" }, { "text": "Performs security operations tasks in Chronicle, including natural-language event search.", "ev": "server/secops/secops_mcp/server.py#L16-17 module docstring of the server" }, { "text": "Gets data into Chronicle through raw log and UDM event ingestion, custom parsers and feed configuration.", "ev": "server/secops/README.md#L253-259 data ingestion and parsing tool category" } ], "use_cases": [ { "text": "Retrieve and monitor security alerts from Chronicle.", "task": "alert-triage", "ev": "server/secops/README.md#L241 documented alert management use" }, { "text": "Run detection rules against historical data as retrohunts and track their results.", "task": "detection-engineering", "ev": "server/secops/README.md#L244 documented threat hunting use" }, { "text": "Look up IPs, domains, hashes and other indicators against Chronicle log history.", "task": "threat-intel-enrichment", "ev": "server/secops/README.md#L242 documented entity analysis use" }, { "text": "Create and deploy rule exclusions to filter false positives and tune detection rules.", "task": "detection-engineering", "ev": "server/secops/README.md#L248 documented rule exclusion use" } ], "not_for": [], "capabilities": { "coverage": "complete", "groups": [ { "name": "Security Tools", "does": "Searches events (natural language or UDM), alerts, entities, IoC matches and rules; asks Gemini; runs retrohunts; creates rules and updates alert status and verdict.", "effects": [ "reads", "changes" ], "enabled": "default", "ev": "server/secops/secops_mcp/tools/security_alerts.py#L285 do_update_security_alert writes alert fields" }, { "name": "Log Ingestion Tools", "does": "Ingests raw logs (single or batch) and pre-formatted UDM events into Chronicle and lists the log types available for ingestion.", "effects": [ "reads", "changes" ], "enabled": "default", "ev": "server/secops/secops_mcp/tools/log_ingestion.py#L127 ingest_raw_log sends logs to Chronicle" }, { "name": "Parser Management Tools", "does": "Creates, lists, reads, activates and deactivates log parsers and tests parser code against sample logs.", "effects": [ "reads", "changes" ], "enabled": "default", "ev": "server/secops/secops_mcp/tools/parser_management.py#L121 create_parser call" }, { "name": "Data Table Management Tools", "does": "Creates data tables for use in detection rules, adds and lists rows, and deletes rows by ID.", "effects": [ "reads", "changes", "deletes" ], "enabled": "default", "ev": "server/secops/secops_mcp/tools/data_table_management.py#L459 delete_data_table_rows call" }, { "name": "Reference List Management Tools", "does": "Creates, reads and updates reference lists (STRING, CIDR or REGEX) used in detection rules; supplied entries replace the existing ones.", "effects": [ "reads", "changes" ], "enabled": "default", "ev": "server/secops/secops_mcp/tools/reference_list_management.py#L324-333 update_reference_list behaviour" }, { "name": "Feed Management Tools", "does": "Lists, reads, creates, updates, enables, disables and deletes ingestion feeds and generates new feed authentication secrets.", "effects": [ "reads", "changes", "deletes" ], "enabled": "default", "ev": "server/secops/secops_mcp/tools/feed_management.py#L500 delete_feed call" }, { "name": "Curated Rules Management Tools", "does": "Lists and reads Google-curated rules, rule sets and detections, and changes rule-set deployment (enabled, precision, alerting).", "effects": [ "reads", "changes" ], "enabled": "default", "ev": "server/secops/secops_mcp/tools/curated_rules_management.py#L701 deployment update call" }, { "name": "Rule Exclusions Management Tools", "does": "Creates, reads, lists and patches rule exclusions, changes their deployment and computes how many events they excluded.", "effects": [ "reads", "changes" ], "enabled": "default", "ev": "server/secops/secops_mcp/tools/rule_exclusions.py#L113 create_rule_exclusion call" }, { "name": "Watchlist Management Tools", "does": "Creates, updates, reads, lists and deletes watchlists that apply risk score multipliers to entities.", "effects": [ "reads", "changes", "deletes" ], "enabled": "default", "ev": "server/secops/secops_mcp/tools/watchlist_management.py#L302 delete_watchlist call" }, { "name": "Investigation Management Tools", "does": "Lists and reads investigations, triggers a new investigation for an alert and fetches investigations linked to alerts or cases.", "effects": [ "reads", "changes" ], "enabled": "default", "ev": "server/secops/secops_mcp/tools/investigation_management.py#L231 trigger_investigation call" } ] }, "architecture": { "summary": { "text": "A Python FastMCP server that the MCP client starts and talks to over stdio; each tool call builds a SecOpsClient from the secops SDK, which calls the Chronicle API in Google Cloud.", "ev": "server/secops/secops_mcp/server.py#L94 server runs with stdio transport" }, "runs": { "where": "local-process", "text": "The MCP client starts the server as a local process (uv, uvx or a bash/pip command) and talks to it over stdio.", "ev": "README.md#L165 author states the stdio transport is used" }, "modes": [ { "where": "local-program", "mode": "standalone", "switch": "uvx --from google-secops-mcp secops_mcp", "text": "After installation the package can be started directly with uvx --from google-secops-mcp secops_mcp.", "ev": "README.md#L65-69 standalone run command" } ], "parts": [ { "name": "MCP client configuration", "zone": "client", "does": "mcpServers entry in the client settings that starts the server and passes CHRONICLE_* and SECOPS_SA_PATH environment variables.", "ev": "server/secops/README.md#L278 client configuration instruction" }, { "name": "secops_mcp server", "zone": "machine", "does": "Python FastMCP process that registers the SecOps tools and serves them over stdio.", "ev": "server/secops/secops_mcp/server.py#L28 FastMCP server object" }, { "name": "secops SDK (SecOpsClient)", "zone": "machine", "does": "Python library the tools call to reach the Chronicle API.", "ev": "server/secops/secops_mcp/server.py#L25 SDK import" }, { "name": "Google Cloud credentials", "zone": "machine", "does": "Application Default Credentials from gcloud, or a service account JSON key file named by SECOPS_SA_PATH.", "ev": "server/secops/README.md#L392-393 service account option" }, { "name": "Chronicle API (Google SecOps)", "zone": "outside", "does": "Google-hosted SIEM instance, selected by project ID, customer ID and region, that runs every search and change the tools request.", "ev": "server/secops/secops_mcp/server.py#L77-78 Chronicle client bound to instance" }, { "name": "Gemini in Chronicle", "zone": "outside", "does": "Model inside SecOps that answers threat intelligence questions sent by get_threat_intel.", "ev": "server/secops/secops_mcp/tools/threat_intel.py#L33 tool docstring names the Gemini model" } ], "listens": [], "connections": [ { "to": "Google SecOps Chronicle API", "kind": "vendor-api", "when": "always", "what": "Sends queries, rule text, log data and configuration changes to the Chronicle instance and receives events, alerts and settings.", "ev": "server/secops/secops_mcp/server.py#L77-79 every tool builds a Chronicle client" }, { "to": "Gemini in Chronicle", "kind": "vendor-api", "when": "optional", "what": "get_threat_intel sends the question text to Chronicle's integrated Gemini model and returns its answer.", "ev": "server/secops/secops_mcp/tools/threat_intel.py#L78 Gemini call" }, { "to": "Chronicle natural-language translation", "kind": "vendor-api", "when": "optional", "what": "search_security_events sends the natural-language query text to Chronicle to translate it into a UDM query.", "ev": "server/secops/secops_mcp/tools/security_events.py#L137 natural-language translation call" } ], "model": { "who": "client", "text": "The AI client's model uses the tools; the repository README names Claude Desktop and the cline.bot VS Code extension as MCP clients.", "ev": "README.md#L3 servers are used by MCP clients" } }, "needs": [ { "kind": "account", "text": "A Google Security Operations (Chronicle) instance, identified by Google Cloud project ID, Chronicle customer ID and region.", "ev": "server/secops/README.md#L360-362 instance variables to set" }, { "kind": "credentials", "text": "Google Cloud Application Default Credentials by default, set up with gcloud auth application-default login.", "ev": "server/secops/README.md#L381-387 default authentication method" }, { "kind": "credentials", "text": "Optionally a service account JSON key file, whose path is read from SECOPS_SA_PATH.", "ev": "server/secops/secops_mcp/server.py#L71-73 service account path from environment" }, { "kind": "runtime", "text": "Python 3.11 or later.", "ev": "server/secops/pyproject.toml#L6 Python requirement" }, { "kind": "tools", "text": "uv (recommended by the author) or pip to install and run the package.", "ev": "server/secops/README.md#L282 uv configuration marked recommended" }, { "kind": "tools", "text": "The gcloud CLI to create Application Default Credentials.", "ev": "server/secops/README.md#L387 authentication command" }, { "kind": "authorization", "text": "Chronicle API access for the identity in use, listed as a requirement for the integration tests.", "ev": "server/secops/tests/README.md#L9 test requirements" }, { "kind": "setting", "text": "CHRONICLE_PROJECT_ID, CHRONICLE_CUSTOMER_ID, CHRONICLE_REGION and SECOPS_SA_PATH are passed through the env block of the MCP client configuration.", "ev": "server/secops/README.md#L296-301 env block of the client configuration" } ], "installer": [ { "text": "The repository README installs the google-secops-mcp package with uv tool install and no version pin.", "ev": "README.md#L44-48 install command without version pin" }, { "text": "The pip client configuration runs /bin/bash -c to install the cloned repository in editable mode with pip install -e . every time the client starts the server.", "ev": "server/secops/README.md#L321-324 pip variant command" }, { "text": "The uv client configuration runs server.py with uv run from a local clone of the repository and loads variables from an env file given with --env-file.", "ev": "server/secops/README.md#L288-294 uv variant arguments" }, { "text": "The package declares its dependencies with minimum versions only, for example secops>=0.35.1 and mcp[cli]>=1.26.0,<2.0, so an install picks the newest matching versions.", "ev": "server/secops/pyproject.toml#L16-23 dependency list with lower bounds" } ], "limits": [ { "text": "If CHRONICLE_PROJECT_ID or CHRONICLE_CUSTOMER_ID is unset, the server falls back to a hard-coded project number and customer ID instead of stopping with an error.", "ev": "server/secops/secops_mcp/server.py#L38-41 hard-coded defaults" }, { "text": "Every tool accepts project_id, customer_id and region arguments that override the configured Chronicle instance for that call.", "ev": "server/secops/secops_mcp/server.py#L60-63 per-call values take precedence" }, { "text": "Without SECOPS_SA_PATH the server creates SecOpsClient() with no explicit credentials, so tools act with whatever default Google credentials the environment provides.", "ev": "server/secops/secops_mcp/server.py#L74-75 ADC fallback" }, { "text": "delete_feed permanently removes a feed and stops its data ingestion; the author states this cannot be undone.", "ev": "server/secops/secops_mcp/tools/feed_management.py#L457-460 delete_feed docstring" }, { "text": "When the API returns it, generate_feed_secret adds the newly generated feed secret to the tool result, so the value reaches the MCP client and its model.", "ev": "server/secops/secops_mcp/tools/feed_management.py#L567-569 secret copied into result" }, { "text": "The server README's pip configuration lists get_ioc_matches, search_security_events and get_security_alerts under autoApprove and get_ioc_matches under alwaysAllow.", "ev": "server/secops/README.md#L333-339 pre-approval lists in example config" }, { "text": "Tool descriptions suggest follow-up write actions to the model, such as updating alert status with do_update_security_alert after an investigation.", "ev": "server/secops/secops_mcp/tools/investigation_management.py#L217-218 next-step text in tool description" }, { "text": "The repository README lists Google's fully managed Remote MCP Server for SecOps as the recommended option ahead of this local server.", "ev": "README.md#L5 recommendation of the remote server" }, { "text": "do_update_security_alert changes an alert's status, priority, severity and verdict, and an empty string clears existing comments or root cause.", "ev": "server/secops/secops_mcp/tools/security_alerts.py#L234-239 use cases of the alert update tool, including clearing fields" }, { "text": "The search_security_events description tells the model to use findings for response actions such as blocking an IP or isolating a host through SOAR or endpoint MCP tools.", "ev": "server/secops/secops_mcp/tools/security_events.py#L91 next-step text in the tool description" }, { "text": "ingest_udm_events writes caller-supplied UDM events into Chronicle, and its description names creating synthetic events for testing detection rules or filling data gaps.", "ev": "server/secops/secops_mcp/tools/log_ingestion.py#L163 workflow note of the UDM ingestion tool" }, { "text": "generate_feed_secret replaces any existing authentication secret of the feed.", "ev": "server/secops/secops_mcp/tools/feed_management.py#L520-521 docstring of generate_feed_secret" }, { "text": "delete_feed passes the feed ID straight to the Chronicle delete call after building the client; the tool has no confirmation parameter or step in code.", "ev": "server/secops/secops_mcp/tools/feed_management.py#L495-500 deletion runs directly after logging and client setup, no confirmation check" }, { "text": "generate_feed_secret creates a new secret for an HTTPS push feed, and its description states that this replaces any existing secret.", "ev": "server/secops/secops_mcp/tools/feed_management.py#L520-521 tool description says the new secret replaces the old one" } ], "not_found": [ { "field": "maturity", "searched": "README.md, server/secops/README.md, server/secops/pyproject.toml, setup.py for preview, experimental, alpha, beta, stable, deprecated, unmaintained" }, { "field": "not_for", "searched": "README.md, server/secops/README.md, server/secops/tests/README.md for out-of-scope, authorised-use or 'do not use' statements" }, { "field": "capability_count", "searched": "README.md and server/secops/README.md for an author-stated number of tools" }, { "field": "listen", "searched": "server/secops/secops_mcp/server.py and all tools/*.py for host, port, bind or HTTP transport; server.run uses transport='stdio'" }, { "field": "autonomy", "searched": "not applicable: entry type is mcp-server, not agent" } ] }, "verdict": null, "runs": [] }