Rank #4 of 4 in Infrastructure as Code
Access
Install
brew install crossplaneShowcase


Try itExperimental
See what an agent can do with Crossplane before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).
$crossplane version --clientrecorded session — replayed, not liveVerified integrations
No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.
By theme — the product's score on each story themeBy theme
Agenticness — how well agents can access and operate the productAgenticnessevidence →
How well agents can access and operate the product
Automation depth — how much of the product can run unattendedAutomation depthevidence →
How much of the product can run unattended
Import migration — stories about import migration in this arenaImport migrationevidence →
Stories about import migration in this arena
Licensing governance — stories about licensing governance in this arenaLicensing governanceevidence →
Stories about licensing governance in this arena
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Plan apply — the plan/apply loop — previewing infrastructure changes and applying them safelyPlan applyevidence →
The plan/apply loop — previewing infrastructure changes and applying them safely
Policy as code — stories about policy as code in this arenaPolicy as codeevidence →
Stories about policy as code in this arena
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
n/a
Providers modules — stories about providers modules in this arenaProviders modulesevidence →
Stories about providers modules in this arena
Secrets config — stories about secrets config in this arenaSecrets configevidence →
Stories about secrets config in this arena
State management — stories about state management in this arenaState managementevidence →
Stories about state management in this arena
Testing validation — stories about testing validation in this arenaTesting validationevidence →
Stories about testing validation in this arena
Story verdicts — every judged story with its evidenceStory verdicts
What’s free: 1 free · 0 paid · 0 enterprise · 19 not stated in evidence
Follow the green: where the map greys out is where Crossplane stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
API surface
Drive the product through a documented public API
✓7/10
unlocks → Webhooks · Official SDKs · MCP server · Machine-readable spec · Versioning policy
Subscribe to events via webhooks
—–
Build against official SDKs
—–
Issue scoped/least-privilege API credentials for an agent
~4/10
Connect an agent via an official MCP server
—0/10
Download a machine-readable API spec (OpenAPI or equivalent)
—0/10
Rely on versioned APIs with a documented deprecation policy
—–
Test against a sandbox environment without touching production data
~4/10
Explore an interactive API reference with runnable examples
—–
Docs for agents
Point an agent at llms.txt or agent-oriented docs
—–
Agentic features
Delegate tasks to a built-in AI assistant inside the product
n/an/a
Operate the product with natural-language commands
—0/10
Plug MCP servers into this product so it can use their tools
n/an/a
Get AI-generated insights and suggestions from my data inside the product
—0/10
Set up automations that run autonomously in the background
~5/10
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
Import migration — stories about import migration in this arenaImport migration
Stories about import migration in this arena
Licensing governance — stories about licensing governance in this arenaLicensing governance
Stories about licensing governance in this arena
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Openness
Self-host the core product
✓9/10
Export all of my data in open formats and leave
~5/10
unlocks → Import existing cloud resources under management and generate matching configuration code · Migrate an existing Terraform-format codebase and its state into this tool
Do everything through the API that I can do in the UI
✓7/10
Read the product's source under an open license
—–
Plan apply — the plan/apply loop — previewing infrastructure changes and applying them safelyPlan apply
The plan/apply loop — previewing infrastructure changes and applying them safely
Get machine-readable plan output (JSON) that an agent can parse to reason about a proposed change
—0/10
Have an agent author an infrastructure change, run a plan headlessly, and present the diff for my approval
~4/10
Drive deployments programmatically from my own application code rather than only through the CLI
~5/10
Plan workflow
Policy as code — stories about policy as code in this arenaPolicy as code
Stories about policy as code in this arena
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Providers modules — stories about providers modules in this arenaProviders modules
Stories about providers modules in this arena
Generate infrastructure code from natural language using AI assistance built into the toolchain
—–
Define infrastructure in a general-purpose programming language with types, loops, and IDE support
~4/10
Consume and publish reusable modules or components from a public registry
~6/10
Manage resources across all major clouds and SaaS providers through a broad provider ecosystem
~6/10
Secrets config — stories about secrets config in this arenaSecrets config
Stories about secrets config in this arena
State management — stories about state management in this arenaState management
Stories about state management in this arena
Testing validation — stories about testing validation in this arenaTesting validation
Stories about testing validation in this arena
Sorted by importance (agentic first) (high → low) · 54/54 stories · click a row’s chevron for the rationale and evidence
Drive the product through a documented public API G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | full | 7/10 | Tprobed | |
Connect an agent via an official MCP server G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | 0/10 | ||
Delegate tasks to a built-in AI assistant inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | n/a | 0/10 | ||
Plug MCP servers into this product so it can use their tools G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | n/a | 0/10 | ||
Run the product headlessly / in CI for automation G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 6/10 | Tprobed | |
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 6/10 | Tprobed | |
Set up automations that run autonomously in the background G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Cclaimed | |
Issue scoped/least-privilege API credentials for an agent G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 4/10 | Cclaimed | |
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Get AI-generated insights and suggestions from my data inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Explore an interactive API reference with runnable examples G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Point an agent at llms.txt or agent-oriented docs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Rely on versioned APIs with a documented deprecation policy G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Test against a sandbox environment without touching production data G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 1 | partial | 4/10 | Tprobed | |
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | fullfree | 9/10 | Tprobed | |
Detect drift between my declared configuration and the actual cloud resources C Drift | platform-engineer | State management — stories about state management in this arenaState management | 3 | full | 8/10 | Xcommunity | |
Consume and publish reusable modules or components from a public registry C Modules | developer | Providers modules — stories about providers modules in this arenaProviders modules | 3 | partial | 6/10 | Cclaimed | |
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | partial | 6/10 | Cclaimed | |
Manage resources across all major clouds and SaaS providers through a broad provider ecosystem C Providers | developer | Providers modules — stories about providers modules in this arenaProviders modules | 3 | partial | 6/10 | Xcommunity | |
Export all of my data in open formats and leave G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | partial | 5/10 | Cclaimed | |
Have an agent author an infrastructure change, run a plan headlessly, and present the diff for my approval C Ai infra ops | ai-native user | Plan apply — the plan/apply loop — previewing infrastructure changes and applying them safelyPlan apply | 3 | partial | 4/10 | Tprobed | |
Get machine-readable plan output (JSON) that an agent can parse to reason about a proposed change C Agent plan parsing | ai-native user | Plan apply — the plan/apply loop — previewing infrastructure changes and applying them safelyPlan apply | 3 | none | 0/10 | ||
Preview exactly what will change — creates, updates, and destroys — before applying C Plan workflow | platform-engineer | Plan apply — the plan/apply loop — previewing infrastructure changes and applying them safelyPlan apply | 3 | none | 0/10 | ||
Run plan and apply non-interactively in CI using saved plan artifacts and approval flags C Plan workflow | devops-lead | Plan apply — the plan/apply loop — previewing infrastructure changes and applying them safelyPlan apply | 3 | none | 0/10 | ||
Enforce policy-as-code checks that block non-compliant infrastructure changes before apply C Policy | devops-lead | Policy as code — stories about policy as code in this arenaPolicy as code | 3 | none | untested | none yet | |
Import existing cloud resources under management and generate matching configuration code G Import | platform-engineer | Import migration — stories about import migration in this arenaImport migration | 3 | none | untested | none yet | |
Pass secrets and sensitive configuration into deployments without exposing them in code or logs C Secrets | developer | Secrets config — stories about secrets config in this arenaSecrets config | 3 | none | untested | none yet | |
Prevent my data from being used to train AI models G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 3 | n/a | untested | none yet | |
Rely on an open license and open governance so the tool cannot be relicensed out from under my company G Licensing | devops-lead | Licensing governance — stories about licensing governance in this arenaLicensing governance | 3 | none | untested | none yet | |
Store state in a remote backend with locking so concurrent runs cannot corrupt it C State backends | platform-engineer | State management — stories about state management in this arenaState management | 3 | n/a | untested | none yet | |
Do everything through the API that I can do in the UI G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | full | 7/10 | Cclaimed | |
Drive deployments programmatically from my own application code rather than only through the CLI G Automation api | developer | Plan apply — the plan/apply loop — previewing infrastructure changes and applying them safelyPlan apply | 2 | partial | 5/10 | Tprobed | |
Write automated tests for my infrastructure code and run them without touching production C Testing | developer | Testing validation — stories about testing validation in this arenaTesting validation | 2 | disputed | 5/10 | Dcontradicted | |
Define infrastructure in a general-purpose programming language with types, loops, and IDE support C Languages | developer | Providers modules — stories about providers modules in this arenaProviders modules | 2 | partial | 4/10 | Cclaimed | |
Let an agent plan and apply with least-privilege credentials and review gates so it cannot make unapproved changes C Ai infra ops | ai-native user | Policy as code — stories about policy as code in this arenaPolicy as code | 2 | partial | 4/10 | Xcommunity | |
Manage per-environment configuration (dev, staging, prod) as separate stacks or workspaces C Config stacks | developer | Secrets config — stories about secrets config in this arenaSecrets config | 2 | partial | 3/10 | Cclaimed | |
Safely inspect and modify state — moving, removing, or renaming resources — when refactoring C State backends | platform-engineer | State management — stories about state management in this arenaState management | 2 | none | 0/10 | ||
Tear down an entire environment cleanly with a destroy operation C Plan workflow | developer | Plan apply — the plan/apply loop — previewing infrastructure changes and applying them safelyPlan apply | 2 | none | 0/10 | ||
Choose where my data is stored (region/residency) G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | n/a | untested | none yet | |
Control data retention and deletion G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | n/a | untested | none yet | |
Encrypt state at rest so credentials and sensitive values are not readable in plaintext state files C State backends | devops-lead | State management — stories about state management in this arenaState management | 2 | none | untested | none yet | |
Generate infrastructure code from natural language using AI assistance built into the toolchain C Ai authoring | ai-native user | Providers modules — stories about providers modules in this arenaProviders modules | 2 | none | untested | none yet | |
Migrate an existing Terraform-format codebase and its state into this tool C Migration | platform-engineer | Import migration — stories about import migration in this arenaImport migration | 2 | none | untested | none yet | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | n/a | untested | none yet | |
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | none | untested | none yet | |
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | none | untested | none yet | |
Rely on documented compatibility promises and upgrade guides between releases C Stability | developer | Licensing governance — stories about licensing governance in this arenaLicensing governance | 2 | none | untested | none yet | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | n/a | untested | none yet | |
Version, review, and roll back my automations G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 1 | partial | 6/10 | Xcommunity | |
Validate and auto-format my configuration before planning C Testing | developer | Testing validation — stories about testing validation in this arenaTesting validation | 1 | partial | 3/10 | Tprobed | |
Target or exclude specific resources in a plan or apply C Plan workflow | platform-engineer | Plan apply — the plan/apply loop — previewing infrastructure changes and applying them safelyPlan apply | 1 | none | 0/10 |
Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 41 stories with headroom
What would move Crossplane’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.
Agenticness — how well agents can access and operate the productConnect an agent via an official MCP server
nonemoves agent-readyimpact 45
Crossplane is a Kubernetes control-plane framework, not an AI agent, so publishing an official MCP server is a plausible ecosystem capability, but no evidence in the pack mentions an MCP server, MCP integration, or agent connectivity of any kind—only marketing language about 'AI systems' acting on APIs, which is not an MCP server claim.
Plan apply — the plan/apply loop — previewing infrastructure changes and applying them safelyRun plan and apply non-interactively in CI using saved plan artifacts and approval flags
nonemoves PA Scoreimpact 30
Crossplane operates as a continuously-reconciling Kubernetes control plane rather than a plan/apply tool with saved plan artifacts and approval gates; the evidence pack contains no documentation of a CI-oriented plan/apply/approve workflow.
Import migration — stories about import migration in this arenaImport existing cloud resources under management and generate matching configuration code
nonemoves PA Scoreimpact 30
Missing: an import/adopt command or workflow, generated MR/Composition code from existing infra, any docs or community reports of migrating pre-existing resources into Crossplane management.
Licensing governance — stories about licensing governance in this arenaRely on an open license and open governance so the tool cannot be relicensed out from under my company
nonemoves PA Scoreimpact 30
Missing: license identification, governance/foundation structure, any statement on relicensing protection.
Policy as code — stories about policy as code in this arenaEnforce policy-as-code checks that block non-compliant infrastructure changes before apply
nonemoves PA Scoreimpact 30
The evidence pack describes Crossplane's control-plane architecture, RBAC, packages, and CLI tooling, but contains no mention of a policy-as-code engine (e.g., OPA/Gatekeeper/Kyverno integration, admission webhooks, or built-in policy checks) that blocks non-compliant infrastructure changes before apply.
Plan apply — the plan/apply loop — previewing infrastructure changes and applying them safelyPreview exactly what will change — creates, updates, and destroys — before applying
nonemoves PA Scoreimpact 30
Missing: any documented `crossplane plan`/diff command showing pending creates/updates/deletes, first-party guidance on previewing resource changes before applying, and independent confirmation of such a preview workflow.
Secrets config — stories about secrets config in this arenaPass secrets and sensitive configuration into deployments without exposing them in code or logs
nonemoves PA Scoreimpact 30
Missing: any documentation or community evidence of secret injection, secure credential storage, or protection from log exposure.
Plan apply — the plan/apply loop — previewing infrastructure changes and applying them safelyGet machine-readable plan output (JSON) that an agent can parse to reason about a proposed change
nonemoves PA Scoreimpact 30
Crossplane's model is continuous reconciliation (drift correction) rather than a discrete plan/apply workflow, and the probe evidence explicitly states no local plan/preview loop exists — every operation requires a live cluster.
Showing the top 8 of 41 — every none/partial verdict in the story verdicts table is headroom.
Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.
Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map4 surfaces · 21 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
Latest docs14 stories
- Run the product headlessly / in CI for automation
- Drive the product through a documented public API
- Set up automations that run autonomously in the background
- Define rules that trigger actions automatically on events
- Version, review, and roll back my automations
- Do everything through the API that I can do in the UI
- Export all of my data in open formats and leave
- Self-host the core product
- Drive deployments programmatically from my own application code rather than only through the CLI
- Define infrastructure in a general-purpose programming language with types, loops, and IDE support
- Consume and publish reusable modules or components from a public registry
- Manage resources across all major clouds and SaaS providers through a broad provider ecosystem
- Manage per-environment configuration (dev, staging, prod) as separate stacks or workspaces
- Detect drift between my declared configuration and the actual cloud resources
CLI docs10 stories
- Run the product headlessly / in CI for automation
- Use an official CLI
- Drive the product through a documented public API
- Test against a sandbox environment without touching production data
- Self-host the core product
- Have an agent author an infrastructure change, run a plan headlessly, and present the diff for my approval
- Drive deployments programmatically from my own application code rather than only through the CLI
- Consume and publish reusable modules or components from a public registry
- Write automated tests for my infrastructure code and run them without touching production
- Validate and auto-format my configuration before planning
crossplane.io9 stories
- Drive the product through a documented public API
- Issue scoped/least-privilege API credentials for an agent
- Set up automations that run autonomously in the background
- Do everything through the API that I can do in the UI
- Have an agent author an infrastructure change, run a plan headlessly, and present the diff for my approval
- Drive deployments programmatically from my own application code rather than only through the CLI
- Let an agent plan and apply with least-privilege credentials and review gates so it cannot make unapproved changes
- Consume and publish reusable modules or components from a public registry
- Manage resources across all major clouds and SaaS providers through a broad provider ecosystem
Hacker News5 stories
- Run the product headlessly / in CI for automation
- Version, review, and roll back my automations
- Let an agent plan and apply with least-privilege credentials and review gates so it cannot make unapproved changes
- Manage resources across all major clouds and SaaS providers through a broad provider ecosystem
- Detect drift between my declared configuration and the actual cloud resources
Probe proofs — replayable recordings from the probe harnessProbe proofs
Replayable recordings from our probe harness — see the Prove-It protocol to submit one.
$crossplane version --clientreproduced$ crossplane version --client Client Version: v2.5.0
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
4 of 8 testable claims verified · 1 contradicted → integrity 25/100
27 distinct capability claims found in Crossplane’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
4
Verified
3
Unverified
1
Contradicted
13
Undersold
Verified (7)
“Managed resources extend Kubernetes to manage external/cloud resources such as AWS RDS instances”
Manage resources across all major clouds and SaaS providers through a broad provider ecosystempartialproof ↗
“Providers connect Crossplane to external APIs, giving broad provider coverage”
Manage resources across all major clouds and SaaS providers through a broad provider ecosystempartialproof ↗
“Composition Revisions let you manage and track changes to Compositions over time”
“Exposes declarative APIs that humans, automation, and AI systems can safely act on”
Drive the product through a documented public APIfullproof ↗
“Automatically corrects drift when software state diverges from desired state”
Detect drift between my declared configuration and the actual cloud resourcesfullproof ↗
“Extends Kubernetes to manage any resource anywhere, not just containers”
Manage resources across all major clouds and SaaS providers through a broad provider ecosystempartialproof ↗
“Ships a broad set of pre-built managed resources covering common cloud needs”
Manage resources across all major clouds and SaaS providers through a broad provider ecosystempartialproof ↗
Unverified (5)
“Functions can be authored in multiple languages including YAML, KCL, Python, and Go”
Define infrastructure in a general-purpose programming language with types, loops, and IDE supportpartialproof ↗
“Supports building, installing, updating, and pushing Crossplane Packages”
Consume and publish reusable modules or components from a public registrypartialproof ↗
“Configurations are portable packages of Crossplane resources that can be shared”
Consume and publish reusable modules or components from a public registrypartialproof ↗
“Environment Configs act as in-memory data stores usable within Compositions”
Manage per-environment configuration (dev, staging, prod) as separate stacks or workspacespartialproof ↗
“Provides a library of reusable components to assemble a platform faster”
Consume and publish reusable modules or components from a public registrypartialproof ↗
Contradicted (1)
“Composition Functions can be tested and rendered standalone without needing a live Kubernetes cluster”
Write automated tests for my infrastructure code and run them without touching productiondisputedproof ↗
Undersold (13)
Run the product headlessly / in CI for automationpartialproof ↗
Issue scoped/least-privilege API credentials for an agentpartialproof ↗
Set up automations that run autonomously in the backgroundpartialproof ↗
Test against a sandbox environment without touching production datapartialproof ↗
Define rules that trigger actions automatically on eventspartialproof ↗
Do everything through the API that I can do in the UIfullproof ↗
Export all of my data in open formats and leavepartialproof ↗
Have an agent author an infrastructure change, run a plan headlessly, and present the diff for my approvalpartialproof ↗
Drive deployments programmatically from my own application code rather than only through the CLIpartialproof ↗
Let an agent plan and apply with least-privilege credentials and review gates so it cannot make unapproved changespartialproof ↗
Validate and auto-format my configuration before planningpartialproof ↗
Claims outside our story set (14)
Real capability claims found in Crossplane’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.
“Lets you configure infrastructure behavior via composable function pipelines instead of writing custom controllers”
source ↗“Installs via a Helm chart”
source ↗“Supports enabling real-time compositions via a feature flag”
source ↗“Can automatically protect Providers from deletion while they have active managed resources”
source ↗“Provides tooling for troubleshooting Compositions, Composite Resources, and Managed Resources”
source ↗“Image Configs give centralized control over package image configuration”
source ↗“Composite Resource Definitions let you define schemas for composite resources (custom APIs)”
source ↗“Extends Kubernetes' RBAC and reliability features to orchestrate more than just containers”
source ↗“New features are introduced behind alpha feature flags, off by default”
source ↗“Lets you design custom APIs and abstractions for how users interact with your control plane”
source ↗“Installing Crossplane enables installation of Provider, Function, and Configuration package resources”
source ↗“Real-time compositions can be enabled via the --enable-realtime-compositions flag”
source ↗“Pre-release versions can be installed from the master Helm channel”
source ↗“Functions extend Crossplane with new ways to configure composition logic”
source ↗
Business model
Apache-2.0 CNCF project with no direct monetization; vendors such as Upbound sell commercial distributions, control planes, and support built on Crossplane.
pricing ↗Score trend
How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.
Try Experimental
Run it in the microterminal →Recorded agent sessions — and a live MCP handshake where the vendor ships one.
Flag
⚑ Flag a verdictThink a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.
For agents
