The section your link pointed to isn't on mcp-security's page any more, so we've brought you to the top.
MCP servers connecting AI clients to Google Security Operations, Threat Intelligence, SOARSOARSecurity orchestration, automation and response, coordinating incident workflows across tools. Playbooks can gather evidence, assign work or carry out approved response actions., and Security Command Center APIs.
Plays4. PlaysWhat you can do nowTo doDoneDismissedDeadlinesSince you lookedChecking Plays…Plays could not be checked. This does not mean there is nothing to do.Plays are held while the actionability and safety checks are measured.Personal Plays are held until the measured rollout checks pass.Deadline reminders are held until the measured rollout checks pass.Sign in to see Plays for your saved tools.Personal Plays and Deadlines are included with Practitioner, Researcher and Business.Sign inSee plansRetrySave a tool in Your stack to see Plays for it.We have not checked every saved tool yet. There is no all-clear to report.No new action was found in the checked release sources. Checked as ofNo published Plays for this tool in the last 90 days. This is not an all-clear for the version you run.No Plays in this view.No dated Plays for your saved tools.Why it mattersDo thisBefore you startEstimated effortEffort has not been measured.Read the sourceSource evidenceAct before it breaksNot for meRemind me next weekHidden from To do until next week.That change was not saved. Try again.Keep my Play answers in my accountOptional: save Done, Not for me and reminders privately in your account. Your tools are matched in this browser. No answers are sent until you opt in.Erase my Play answersYour Play answers and private calendar link have been erased.Create a private calendar linkReplace calendar linkRevoke calendar linkAnyone with this link can read generic deadline events. It contains no tool names, versions or answers. Revoke it any time.Private calendar feedWithin 30 daysWithin 7 daysPast the published dateMore than 30 days awayAct byNo earlier visit saved for this tool.breakingtotal Plays since your last reviewReview this toolMark this tool reviewedReview dates stay in this browser. Opening this list does not mark a tool reviewed.Category moves this monthThere is not enough documented history to call a category move this month.Category history is unavailable. No monthly comparison can be made.Category moves are held until the measured rollout checks pass.The documented monthly history shows no category move.What we got wrongThere are too few reviewed Plays to report a correction rate.Play corrections have not been measured for this month.Plays reviewedcorrectedPublished in the last 90 days. Breaking changes come first.Saved tools are matched in this browser; your versions are not sent.Your Plays{count} PlaysWhat you can do with the tools you runRelease sources for {checked} of {total} saved tools checked; no new plays match this edition.Add your toolsRead the details on the webIn {count} daysWe corrected {wrong} of {count} reviewed Plays.
Summary
mcp-security is an open-source MCP-tooling server that gives AI clients access to Google SecOpsSecOpsThe practice of merging security and IT operations teams so that threat detection, response, and infrastructure management share the same workflows, giving cyber tools a single pipeline from alert to remediation., Threat Intelligence, SOAR, and Security Command Center APIs, with no licence cost. It runs as separate local packages through uv or pip, or through a managed remote server, using Google authentication; blue-team practitioners can select only the services their workflows need. Its README presents it as an MCP interface for Claude Desktop and the Cline VS Code extension rather than a standalone SIEMSIEMSecurity information and event management, collecting logs from many systems and correlating events to find suspicious activity. Analysts use it to investigate alerts and incidents., with tools for UDM and event searches, detection-rule exclusions, and SOAR integrations. Ongoing releases add capabilities and authentication options.
MCP servers connecting AI clients to Google Security Operations, Threat Intelligence, SOAR, and Security Command Center APIs.
Which security events in my Google SecOps environment match an investigation timeframe or query?
searches UDM records and events through Google SecOps and returns results scoped to the supplied time range; the answer is limited to data available through the authenticated SecOps service
Which detection-rule exclusions are affecting my SecOps detections?
retrieves and manages exclusions for detection rules, showing the exclusions available to the authenticated SecOps account and allowing authorized changes
What threat intelligence is available about an indicator or threat relevant to my investigation?
queries Google Threat Intelligence through the selected MCP service and returns the intelligence exposed for that indicator or threat; coverage depends on the account and service data
What cloud security risks are reported for my environment?
accesses findings and risk information from Security Command Center and presents what that service returns for the authenticated cloud environment
What response actions or integrations can I use for an incident?
connects an AI client to Google SecOps SOAR and its configured integrations so it can inspect or invoke the response capabilities exposed by the authorized SOAR account; available actions depend on that account's integrations and permissions
Built from mcp-security's releases, docs, README and our own runs.
“Seen” marks the month we first spotted a release the vendor didn't date.
Group names and tags are our labels.
+MCP server connectivity for Google Security productsNot checked yet · Date unknownProvides MCP servers that connect AI clients to Google Security Operations, Google Threat Intelligence, SOAR, and Security Command Center APIs.5 other sources▸
Also counts toward: MCP server
+Log parser enumerationNot checked yet · Date unknownAllows practitioners to list the available log parsers in the SecOps service.1 release · first seen Aug 2026▸
+Detection rule exclusions managementNot checked yet · Date unknownEnables practitioners to create, update, and manage exclusions for detection rules in the SecOps service.1 release · first seen Mar 2026▸
+Service account authenticationNot checked yet · Date unknownSupports service account credentials as an authentication option for connecting to the SecOps service.1 release · first seen Feb 2026▸
+MCP server execution mode selectionNot checked yet · Date unknownAllows practitioners to choose between remote and local execution when running MCP server skills.1 release · first seen Feb 2026▸
+UDM and event searchNot checked yet · Date unknownSearch UDM records and events within the SecOps service, with support for scoped time-range queries via custom start and end time parameters.1 release · first seen Jan 2026▸
Lines in monospace are the tool's own words: help text
parsed from its source, or an endpoint from its API document. Under
release, a line is our summary of a dated release. Under
docs, it is quoted from the tool's own documentation or
website. Each links back to the source it came from.
Command line
View
load a captured run
composed command
No matchesTry a different search, or clear a filter to see more.
option surface across analysed releases
options at that releaseadded, per releaseremoved, per release
option
found in
since
description
No matchesTry a different search, or clear a filter to see more.
option changes per release — drag across the rail to set a range
→
Values are placeholders taken from each option’s declared default.
Nothing is executed here — the output shown is a recording of a run
that already happened.
Score card
Shipping velocityreleases a month, last 12 months
Documentation qualityrelease-notes rubric, 0–100
Breaking-change disciplinehow rarely a release breaks users, and notice given
Maintenance riskquiet time against its own cadence, maintainers
Innovation & surfacenew capabilities, API and MCP surface
Community health
Contributor trenddistinct committers, this year against last
Maintainer concentrationbus factor now against a year ago
Issue backlog trendissues closed per issue opened, 12 months
Responsivenessmedian time to a maintainer’s first reply
Nine scores for mcp-security, each built from the releases, notes and API history this site tracks — and, on Researcher and Business, where it stands among every measured tool in its category and how that has moved.
Each score is 0–100 on a published rubric, derived from data this site already shows.
A dimension we cannot measure says so — it is never scored 0 and never enters a rank.
How this is scored
Shipping velocity — releases a month over the last 12 months, on a log scale where 16 a month scores 100. Needs 3 releases in the window.
Documentation quality — the release-notes rubric published on the analytics page, unchanged.
Breaking-change discipline — the share of releases carrying a breaking change (none scores 100, half or more scores 0). Only projects that label breaking changes are measured: a clean record cannot be told from an unlabelled one.
Maintenance risk — quiet time measured against the tool's own release cadence (quiet longer than 90 days and three typical gaps scores 0), plus the number of active maintainers and whether contributors are growing, where known. Higher is lower risk.
Innovation & surface — new capabilities in the feature ledger this year, API and MCP operations added, and the share of commits that are features: the mean of whichever we hold.
Community health (open-source tools only) — each is a direction, not a size: contributors this year against last, the bus factor now against a year ago, and issues closed per issue opened, where steady scores 50, doubled 100 and halved 0; plus the median time to a maintainer's first reply (an hour scores about 100, a month or more 0). A commercial card has no repository and carries none of the four.
Documented delivery (commercial tools) — when a vendor's documented new capabilities have slowed against its own baseline, that counts against the overall standing as heavily as two low dimensions. Steady delivery, or too little history to judge, leaves the standing alone; it is never a sixth score.
Open-source tools are scored on repository signals; commercial tools on their published changelog. Ranks compare tools within one category and one profile and need at least five measured peers; the overall standing needs three ranked dimensions. Best-in-breed or consolidator is a shape, not a quality, and is never scored.
Release-note detail over time
See how much detail mcp-security puts in its release notes, quarter by quarter, and compare it with tracked tools in the same category. This history uses up to ten retained, reviewed notes per tool; sparse or blank older quarters may reflect that limit.
Issue, contributor and maintainer activity in google/mcp-security, 2023-12 – 2026-11,
as of 2026-11-03. Twelve-month figures first; the trend lines run
the whole window.
Contributorsnot measureddistinct committers, last 12 months
Maintainersnot measuredcore set, last 12 months
Bus factornot measuredcommitters behind half the commits
Community-filed59%of issues opened, last 12 months
Median time to close374 daysfirst maintainer reply 17 days
Open backlog24of 70 issues ever filed
Issues opened / month0 · 1communitymaintainers
Open backlog24
Contributors / monthnot measured
Commits / monthnot measured
Starsnot measured
Issue themes, last 12 months
features 4%
other 96%
Counts from the project's public repository and git history; no individuals
are identified. Maintainers are the committers covering 80% of the last year's
commits. how we measure this
Ships a vulnerable library
What its latest release locks, checked against known advisories.
google-cloud-aiplatform 1.97.0 in its run-with-google-adk image
high
mcp-security secops-v0.7.1 builds its run-with-google-adk image from run-with-google-adk/requirements.txt, which locks google-cloud-aiplatform 1.97.0. That version has GHSA-wh2j-26j7-9728.
Fixed in google-cloud-aiplatform 1.133.0. No mcp-security release includes it yet.
Copy this, send it to your AI assistant, then come back with its reply.
Nothing is sent from here. You paste the reply in the next step.
1 Copy
2 Paste
3 Confirm
Paste the reply
One tool per line is best. Versions are optional, and any format works. Names we don’t track are sent to us, without versions, so we can consider adding them.