The section your link pointed to isn't on DeepSource's page any more, so we've brought you to the top.
DeepSource is an automated code review platform that analyzes code for bugs, security vulnerabilities, anti-patterns, and style issues across multiple languages.
DeepSource is a commercial appsec platform that runs static analysis, software composition analysissoftware composition analysisSoftware composition analysis, identifying third-party dependencies and checking them for known vulnerabilities and license issues. It covers software a team uses rather than writes itself., and AI-driven code review against an organization's repositories, offered as a hosted service with an Enterprise Server option for self-hosted deployments. It targets application development and platform teams who need vulnerability and code-quality checks built into their pull request workflow rather than a separate scanning step. AI Review can be scoped to run only when explicitly mentioned in PR comments, billed by processed lines of code, and for Enterprise Server customers its Bring Your Own Key support routes model inference directly to Azure OpenAI or GCP Vertex AI instead of through DeepSource's own cloud, which matters for teams with data residency constraints. It also exposes an MCPMCPModel Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server so AI coding agents can pull review results and repository metrics directly.
DeepSource is an automated code review platform that analyzes code for bugs, security vulnerabilities, anti-patterns, and style issues across multiple languages.
Which of my pull requests introduce a security vulnerability or bug before they merge?
runs static analysis and AI-driven review against the changed code and flags issues by file and line as part of the PR workflow, rather than as a separate scan someone has to remember to run
Which of my dependencies carry a known CVE, and did that change since yesterday?
checks packages and lock files against vulnerability databases every hour and re-scans affected repositories automatically when a new CVE matches something in use, sending a digest to org admins
Which sub-project in this monorepo is the one pulling in the vulnerable package?
scopes the dependency view to each sub-repository's own packages and lock files, so a monorepo with many services shows a separate dependencies tab per sub-project instead of one undifferentiated list
Can my AI coding agent pull a repository's review findings without me pasting them in?
exposes review results, vulnerability data, and repository metrics through an MCP server the agent can query directly
Do I need to send my code to an external cloud to get AI-driven review?
on Enterprise Server, Bring Your Own Key routes model inference straight to an organization's own Azure OpenAI or GCP Vertex AI account instead of through DeepSource's cloud
Is AI review going to run - and get billed - on every pull request whether I want it to or not?
can be limited to trigger only when a PR comment explicitly mentions the bot, and usage is billed on a single processed-lines-of-code metric rather than per-check or per-feature
Built from DeepSource'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.
Launches the DeepSource Directory, a central place to explore code quality and SAST checkers across 20+ Analyzers
DeepSource Directory, Globstar improvements · Feb 2025
· source
· release history
+Globstar Checker DevelopmentshippedAllows users to write and run custom checkers in Go or YAML using tree-sitter syntax via a `.globstar/` directory.1 release · first seen Feb 2025▸
Also counts toward: User-defined detection rules, Plugin system, Scripting API
release
Enables writing Globstar checkers in Go with an all-new API for tree-sitter scope resolution and multi-file analysis
DeepSource Directory, Globstar improvements · Feb 2025
· source
· release history
+Software Composition Analysis (SCA)shippedScans repository dependencies for known vulnerabilities by monitoring multiple CVE databases hourly, automatically re-scanning affected repositories, and supporting monorepos with per-sub-repository dependency views.13 releases · 1 other source · first seen Apr 2023▸
Continuously monitors multiple vulnerability databases every hour and automatically re-scans affected repositories when newly published CVEs match dependencies, sending digest emails to org admins.
AI Review on more programming languages · seen Jul 2026
· source
· release history
Runs SCA on monorepos with per-sub-repository Dependencies tabs, scoped to each sub-project's packages and lock files.
AI Review on more programming languages · seen Jul 2026
· source
· release history
Adds configurable preferences for new open-source dependency vulnerability alerts, including notification recipients and severity thresholds, via Policies → OSS Vulnerabilities → New Vulnerability Alerts.
AI Review on more programming languages · seen Jul 2026
· source
· release history
pom.xml Java projects now have Reachable or Unreachable vulnerability labels based on bytecode-level reachability analysis.
AI Review on more programming languages · Jul 2026
· source
· release history
Sub-repositories in monorepos each get a scoped Dependencies tab using their own or the root lock file.
AI Review on more programming languages · Jul 2026
· source
· release history
Policies -> OSS Vulnerabilities -> New Vulnerability Alerts allows configuring notification recipients and severity thresholds for new open-source dependency advisories.
AI Review on more programming languages · Jul 2026
· source
· release history
example
Configure notification preferences for new open-source dependency vulnerability alerts via the UI.$ In the DeepSource dashboard, head to Policies -> OSS Vulnerabilities -> New Vulnerability Alerts and set who gets notified and at what severity threshold.
AI Review on more programming languages · Jul 2026
· source
+MCP server1 featureInterfaces and integrationssince 2023▸
+MCP Server integrationshippedExposes code review results, vulnerability data, and repository metrics to AI coding agents via the Model Context Protocol.12 releases · 3 other sources · first seen Jan 2023▸
Shared capability: MCP server
Also counts toward: MCP server, Single sign-on, SAML SSO
release
12 total
Adds DeepSource MCP Server exposing 30 tools across 8 categories so AI coding agents can access code review results, vulnerability data, and repository metrics via the Model Context Protocol.
AI Review on more programming languages · seen Jul 2026
· source
· release history
The DeepSource MCP Server exposes 30 tools across 8 categories via the Model Context Protocol, installed using add-mcp from NPM with OAuth authentication.
AI Review on more programming languages · Jul 2026
· source
· release history
Adds add-mcp utility from NPM for installing the DeepSource MCP Server integration with AI coding agents.
DeepSource MCP Server · Apr 2026
· source
· release history
New CLI v2 releases with JSON output and AI agent skill integration for automated code review workflows.
DeepSource CLI v2 · Mar 2026
· source
· release history
Exposes new GraphQL types for retrieving AI issues, OSS vulnerabilities, and PR report card data
The AI Code Review Platform · Feb 2026
· source
· release history
Adds code_formatters type to the Public API, replacing the deprecated transformers type.
Code formatters, team invitations, performance improvements · Dec 2025
· source
· release history
example
Install the DeepSource MCP Server for an AI coding agent using NPM.$ npx add-mcp deepsource --auth=oauth
AI Review on more programming languages · Jul 2026
· source
Install the DeepSource MCP Server for an AI agent using the NPM utility$ npx add-mcp https://mcp.deepsource.com/mcp
DeepSource MCP Server · Apr 2026
· source
Run custom defined checkers against your codebase after creating a .globstar/ directory.$ globstar check
Introducing Globstar: Open-source Static Analysis Toolkit · Jan 2025
· source
+UV Package Manager SupportshippedAdds support for the `uv` package manager in DeepSource SCA for Python projects.1 release · first seen Jun 2025▸
Shared capability: Dependency scanning
release
Adds uv package manager support in DeepSource SCA for Python projects.
Bun and uv are now supported in DeepSource SCA · Jun 2025
· source
· release history
+Other / not yet classified14 featuresFeatures we have not matched to a capability yet. A suggested match is marked.▸
+AI ReviewshippedsuggestedAutomatically reviews pull requests using AI, supporting languages without a DeepSource static analyzer, with configurable trigger modes, tiered plans, and usage billed by processed lines of code.62 releases · 1 other source · first seen Jan 2022▸
Suggested capability: Static application security testing. This is our guess, not confirmed.
release
62 total
Simplifies AI Review billing to a single blended metric: processed lines of code (LOC).
AI Review on more programming languages · seen Jul 2026
· source
· release history
Enables AI Review to run on-demand only when @deepsourcebot is mentioned in PR comments.
AI Review on more programming languages · seen Jul 2026
· source
· release history
Expands AI Review to ten additional programming languages that lack a DeepSource static analyzer.
AI Review on more programming languages · seen Jul 2026
· source
· release history
Introduces two AI Review tiers (Standard and Advanced), with Team plan users defaulted to Standard.
AI Review on more programming languages · seen Jul 2026
· source
· release history
AI Review can be configured to trigger only when @deepsourcebot is mentioned in PR comments.
AI Review on more programming languages · Jul 2026
· source
· release history
Settings → Code Review → Analyzers enables AI Review for ten languages that previously lacked a static analyzer.
AI Review on more programming languages · Jul 2026
· source
· release history
example
Turn on AI Review for a newly supported language that has no DeepSource static analyzer.$ In the DeepSource dashboard, go to Settings → Code Review → Analyzers, pick the target language, and click Save changes.
AI Review on more programming languages · seen Jul 2026
· source
+Enterprise Server deploymentshippedHosts DeepSource on-premises or in private infrastructure, with support for Kubernetes Gateway API routing and Bring Your Own Key model provider credentials for AI Review inference.7 releases · 2 other sources · first seen May 2022▸
Also counts toward: Kubernetes-native deployment, Self-hosted deployment
release
7 total
Supports Bring Your Own Key (BYOK) model provider credentials for Enterprise Server AI Review, routing inference directly to Azure OpenAI or GCP Vertex AI without passing through DeepSource Cloud.
AI Review on more programming languages · seen Jul 2026
· source
· release history
Supports Kubernetes Gateway API on Enterprise Server, creating HTTPRoutes attached to an existing Gateway instead of an Ingress.
AI Review on more programming languages · seen Jul 2026
· source
· release history
Admin Console setting Use Gateway API? (Yes/No) with gateway name and namespace configures DeepSource to create HTTPRoute resources instead of Ingresses.
AI Review on more programming languages · Jul 2026
· source
· release history
Enables Kubernetes Gateway API support in Enterprise Server via Admin Console configuration.
OSS vulnerability scanning for monorepos · May 2026
· source
· release history
--skip-tls-verify flag in the DeepSource CLI for on-prem installations with self-signed certificates.
.NET 10, Windows CLI, and PR feedback · Mar 2026
· source
· release history
Requires running the new kube-janitor service to clean up old jobs in the atlas-jobs namespace before upgrading the Enterprise Server version.
Composite Test Coverage Metric · Nov 2022
· source
· release history
example
Enable Kubernetes Gateway API on Enterprise Server so DeepSource creates HTTPRoutes instead of Ingress resources, keeping traffic within your existing Gateway.$ In the Admin Console, go to Config, set 'Use Gateway API?' to Yes, then provide your Gateway name and namespace.
AI Review on more programming languages · seen Jul 2026
· source
Configure DeepSource Enterprise Server to use the Kubernetes Gateway API instead of Ingress resources.$ In the Admin Console, go to Config and set `Use Gateway API?` to `Yes`, then provide your Gateway name and namespace.
AI Review on more programming languages · Jul 2026
· source
+Webhook IntegrationshippedExposes event-driven notifications for code health status changes, including analyzer run updates, issue lifecycle events, team member changes, and autofix progress.8 releases · first seen Jan 2022▸
Also counts toward: Outbound webhooks (the product notifies you)
release
8 total
Adds autofix_run.updated webhook event that triggers when the status of the corresponding PR of an Autofix is updated
New webhook events · Dec 2022
· source
· release history
Adds repository_issue.resolved webhook event that triggers when an issue is resolved in the default branch of a repository
New webhook events · Dec 2022
· source
· release history
Adds autofix_run.started webhook event that triggers when a new Autofix is created
New webhook events · Dec 2022
· source
· release history
Adds repository_issue.resolved webhook event to trigger when an issue is resolved in the default branch.
New webhook events · Apr 2022
· source
· release history
Adds autofix_run.updated webhook event to trigger when the status of the corresponding PR of an Autofix is updated.
New webhook events · Apr 2022
· source
· release history
Adds autofix_run.started webhook event to trigger when a new Autofix is created.
New webhook events · Apr 2022
· source
· release history
+Vulnerability Notification ControlsshippedProvides granular configuration for open-source vulnerability alerts, including severity thresholds and recipient selection.3 releases · first seen Apr 2026▸
Also counts toward: Web management console
release
Adds UI path Policies -> OSS Vulnerabilities -> New Vulnerability Alerts to control OSS dependency alert notifications
Configure New Vulnerability Alerts · Apr 2026
· source
· release history
Adds option to set notification severity threshold (critical, high, medium, low) for new open-source vulnerabilities
Configure New Vulnerability Alerts · Apr 2026
· source
· release history
Adds toggle to include all organization admins in vulnerability alert notifications
Configure New Vulnerability Alerts · Apr 2026
· source
· release history
+REST API ExpansionshippedAdds GraphQL endpoints for PR report cards and a broader REST API surface for retrieving findings, metrics, and compliance data.2 releases · first seen Feb 2026▸
Also counts toward: GraphQL API support, REST API
release
Exposes 30 tools across 8 categories for accessing pull request findings, PR report card grades, dependency vulnerability reachability, code coverage metrics, compliance reports (OWASP Top 10, SANS Top 25), and issue suppression rules.
DeepSource MCP Server · Apr 2026
· source
· release history
Exposes new GraphQL types for retrieving AI issues, OSS vulnerabilities, and PR report card data
The AI Code Review Platform · Feb 2026
· source
· release history
+PR Report CardshippedGenerates quality grades across multiple dimensions for pull requests and exposes these insights in PR comments, exports, and API queries.2 releases · first seen Feb 2026▸
release
PR Report Card insights included in pull request comments and Copy as Markdown exports.
.NET 10, Windows CLI, and PR feedback · Mar 2026
· source
· release history
Generates a PR Report Card with grades A-D across Security, Reliability, Complexity, Hygiene, and Coverage dimensions for every reviewed pull request
The AI Code Review Platform · Feb 2026
· source
· release history
+OIDC AuthenticationshippedEnables OpenID Connect authentication for GitHub Actions workflows.2 releases · first seen May 2025▸
Also counts toward: CI/CD pipeline integration, OIDC SSO
release
Introduces a provider selection screen during login for users who have access to multiple IDPs
SSO multi-IDP support · Jan 2026
· source
· release history
Supports OpenID Connect (OIDC) authentication for GitHub Actions workflows
DeepSource Agents, Autofix AI, OIDC support · May 2025
· source
· release history
+Custom Linter Support via SARIFshippedsuggestedEnables the use of third-party or custom static analysis tools by accepting SARIF reports in CI pipelines, specifically supporting linters such as Kube Linter, Dart Analyze, Slither, and AWS CloudFormation Linter.2 releases · first seen Jan 2024▸
Suggested capability: Static application security testing. This is our guess, not confirmed.
Also counts toward: CI/CD pipeline integration, User-defined detection rules
release
Adds support for writing custom checkers in .globstar/ directory using YAML format with tree-sitter S-expression syntax
Introducing Globstar: Open-source Static Analysis Toolkit · Jan 2025
· source
· release history
New Community Analyzers feature supporting Kube Linter, Dart Analyze, Slither, and AWS CloudFormation Linter via SARIF reports in CI pipelines
Community Analyzers · Jan 2024
· source
· release history
+External Reporting and VisibilityshippedAllows sharing of repository or team code health reports via public links with optional password protection, and pinning specific reports on the dashboard.2 releases · first seen Nov 2022▸
release
Adds the ability to pin specific reports on the DeepSource dashboard at both team and repository levels via the ellipsis menu
Pinned Reports · Dec 2022
· source
· release history
Adds Public Reports feature to share external links for repository or team reports, with optional password protection.
Composite Test Coverage Metric · Nov 2022
· source
· release history
+OAuth AuthenticationshippedEnables authentication via OAuth flows, allowing integration without manual token configuration.1 release · first seen Apr 2026▸
release
Enables authentication via OAuth without manual token configuration.
DeepSource MCP Server · Apr 2026
· source
· release history
+Inline Review CommentsshippedEnables reviewers to post comments directly on pull request diffs across supported version control systems.1 release · first seen Feb 2026▸
release
Enables inline review comments on pull request diffs for GitHub, GitLab, Bitbucket (Cloud and Data Center), and Azure DevOps Services via the Settings > Quality Gates toggle
The AI Code Review Platform · Feb 2026
· source
· release history
+AI Review AutofixshippedUses LLMs to generate context-aware code remediations within the AI Review capability.1 release · first seen May 2025▸
release
Enables Autofix™ AI mode via Team Settings to generate context-aware remediations using LLMs
DeepSource Agents, Autofix AI, OIDC support · May 2025
· source
· release history
+DeepSource AgentsshippedProvides autonomous agents for code analysis tasks including autofix autopilot, CVE prioritization, and false positive triage.1 release · first seen May 2025▸
Also counts toward: Autonomous investigation and remediation
release
Adds DeepSource Agents for autonomous code analysis including Autofix™ Autopilot, CVE Prioritization Agent, and False Positive Triage Agent
DeepSource Agents, Autofix AI, OIDC support · May 2025
· source
· release history
+Vanta IntegrationshippedsuggestedIntegrates SCA data with Vanta to surface vulnerable dependencies in the Vanta dashboard.1 release · first seen May 2025▸
Suggested capability: Vulnerability database matching. This is our guess, not confirmed.
release
Integrates Software Composition Analysis (SCA) with Vanta to surface vulnerable dependencies in the Vanta dashboard
DeepSource Agents, Autofix AI, OIDC support · May 2025
· source
· release history
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
3 commands for DeepSource, each
with where it came from. This tool has no source analysis yet, so there
is no option reference and no captured run beside them.
View
Source
No command matches.
Screenshots
From the release notes, newest first. Click one to see it full size.
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
Five scores for DeepSource, 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 DeepSource 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.