by Anatoly Koptev
Self-hosted MCP server that gives coding agents a call graph and review memory
Krolik is the product name for Vaelor, an Go engine with 1,422 commits that parses code with tree-sitter and stores it in Apache AGE. You run it yourself with Docker and point your agent at a local MCP URL. Expect to operate Postgres and an embedder if you want the full tool set.
debug_investigate: a 7-phase pipeline that bridges Prometheus alerts and Jaeger traces to the root-cause file:function in 5 seconds, a capability no other free MCP server provides.
Open source and easy to fork; the moat is the depth of the debug pipeline and taint analysis, which take real engineering effort to replicate. But competitors with larger communities can catch up.
Main trade-off
2 GitHub stars as of June 2026: effectively zero community support, no external documentation, and no indication of production adoption.
Free and open source under Apache 2.0, self-hosted only. Vaelor's site says there is no hosted SaaS and no signup, so there is no plan to buy. Your running costs are your own server and, for the LLM-backed tools, an OpenAI-compatible endpoint of your choice. The agent client you attach it to is billed separately.
claude mcp add -s user -t http vaelor http://127.0.0.1:8897/mcp
Exposed as MCP tools over Streamable HTTP on port 8897. Register the URL with your client (command under install). The agent calls tools by name (for example call_trace, understand, impact_analysis) with JSON arguments.
The permissions this connector asks for, as its own documentation states them.
26 actions an agent can call. Open one for its parameters and an example.
Example call
{"arguments":{"depth":4,"query":"rate(http_requests_total{status=\"500\"}[5m]) > 0.1"},"tool":"debug_investigate"}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| query | string | Required | The error message, Prometheus alert expression, or Jaeger trace to investigate. |
| depth | numberdefault 3 | Optional | How many call levels to trace when following the root-cause hypothesis. |
Returns
| Field | Type | Description |
|---|---|---|
| root_cause | string | File path and function name identified as the root cause. |
| hypothesis | string | Explanation of the failure chain. |
Example call
{"arguments":{"limit":10,"query":"user authentication token validation"},"tool":"semantic_search"}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| query | string | Required | Natural language description of the code to find. |
| limit | numberdefault 10 | Optional | Maximum number of results to return. |
Returns
| Field | Type | Description |
|---|---|---|
| results | array | Ranked list of file paths, symbol names, and relevance scores. |
Example call
{"tool": "symbol_search", "arguments": {"pattern": "HandleAuth*", "language": "go"}}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| pattern | string | Required | Name pattern to match, supports wildcards. |
| language | string | Optional | Filter results to one language (e.g. 'go', 'python', 'typescript'). |
Returns
| Field | Type | Description |
|---|---|---|
| symbols | array | List of matching symbol names with file path and line number. |
Example call
{"tool": "call_trace", "arguments": {"symbol": "CreateOrder", "direction": "up", "depth": 5}}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| symbol | string | Required | Fully qualified or partial function or method name to trace. |
| direction | stringdefault up | Optional | Trace direction: 'up' to find callers or 'down' to find callees. |
| depth | numberdefault 5 | Optional | Maximum number of call levels to follow. |
Returns
| Field | Type | Description |
|---|---|---|
| call_chain | object | Tree structure of the call chain with file paths and line numbers. |
Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| symbol | string | Required | Symbol name to analyze for change impact. |
| depth | numberdefault 5 | Optional | Maximum traversal depth for impact calculation, up to 10. |
Returns
| Field | Type | Description |
|---|---|---|
| affected_symbols | array | List of symbols affected by a change, with their file paths and distance from the target. |
Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| symbol | string | Required | Starting function or symbol to trace dataflow from. |
| source | string | Optional | Taint source to track (e.g. an HTTP input function). |
Returns
| Field | Type | Description |
|---|---|---|
| taint_paths | array | List of taint flow paths from source to potential sinks, with file and line numbers. |
Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| pattern | string | Required | Tree-sitter AST pattern to find, supports $x wildcard bindings. |
| replacement | string | Required | Replacement pattern using the same $x bindings. |
| language | string | Optional | Language to run the rewrite in. Omit to apply across all indexed files. |
Returns
| Field | Type | Description |
|---|---|---|
| changed_files | array | List of files modified with change counts per file. |
Example call
{"tool": "review_pr", "arguments": {"pr_url": "https://github.com/org/repo/pull/42"}}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| pr_url | string | Optional | GitHub pull request URL to analyze. |
| diff | string | Optional | Raw unified diff text if no PR URL is available. |
Returns
| Field | Type | Description |
|---|---|---|
| review | object | Blast radius, risk score, and list of affected symbols with file paths. |
Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| symbol | string | Required | Symbol to analyse, fully or partly qualified. |
Returns
| Field | Type | Description |
|---|---|---|
| analysis | object | Type signature, call count, complexity score, and all references in the codebase. |
Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| query | string | Required | Natural language question about code relationships. |
| depth | numberdefault 3 | Optional | Maximum graph traversal depth for the generated Cypher query. |
Returns
| Field | Type | Description |
|---|---|---|
| graph_results | array | Matching nodes and edges from the knowledge graph with file and line metadata. |
Example call
{"tool": "dead_code", "arguments": {"language": "typescript", "threshold": 0.8}}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| language | string | Optional | Restrict analysis to one language. Omit to scan all indexed languages. |
| threshold | numberdefault 0.7 | Optional | Confidence threshold (0.0 to 1.0) above which a symbol is reported as dead. |
Returns
| Field | Type | Description |
|---|---|---|
| dead_symbols | array | List of likely-unused symbols with confidence scores and file paths. |
Example call
{"tool": "code_health", "arguments": {}}Returns
| Field | Type | Description |
|---|---|---|
| grade | string | Letter grade A through F for overall code health. |
| breakdown | object | Per-category scores: dead code, complexity, dependencies, test coverage. |
Example call
{"tool": "repo_analyze", "arguments": {"repo_path": "/workspace/my-service", "mode": "deep"}}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| repo_path | string | Required | Absolute path or GitHub URL of the repository to analyze. |
| mode | stringdefault quick | Optional | Analysis mode: 'deep' for full indexing, 'quick' for overview, 'issues' or 'prs' for issue/PR context. |
Returns
| Field | Type | Description |
|---|---|---|
| analysis | object | Repository overview including languages, key modules, health grade, and open issues summary. |
Example call
{"tool": "explore", "arguments": {"repo_url": "https://github.com/org/repo"}}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| repo_url | string | Optional | GitHub repository URL. Omit to explore the currently indexed workspace. |
Returns
| Field | Type | Description |
|---|---|---|
| overview | object | Repository name, primary language, file count, key entry points, and README summary. |
Example call
{"tool": "file_parse", "arguments": {"file_path": "src/auth/token.go", "output": "symbols"}}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| file_path | string | Required | Relative or absolute path to the file to parse. |
| output | stringdefault symbols | Optional | Output format: 'symbols' for a flat list or 'ast' for the full AST. |
Returns
| Field | Type | Description |
|---|---|---|
| result | object | Parsed symbols or AST depending on the output parameter. |
Example call
{"tool": "dep_graph", "arguments": {"format": "mermaid"}}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| format | stringdefault json | Optional | Output format: 'mermaid', 'graphviz', or 'json'. |
Returns
| Field | Type | Description |
|---|---|---|
| graph | string | Dependency graph in the requested format. |
Example call
{"tool": "code_compare", "arguments": {"repo1": "https://github.com/org/service-v1", "repo2": "https://github.com/org/service-v2"}}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| repo1 | string | Required | Path or URL of the first repository. |
| repo2 | string | Required | The repository to compare against, as a path or URL. |
Returns
| Field | Type | Description |
|---|---|---|
| comparison | object | Side-by-side comparison of architecture patterns, API symbols, and quality scores. |
Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| symbol | string | Required | Symbol to be changed. |
| change_description | string | Required | Plain English description of the intended change. |
Returns
| Field | Type | Description |
|---|---|---|
| risk_report | object | Risk score, list of affected tests, downstream services, and recommended validation steps. |
Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| query | string | Required | Plain-English research question about the codebase. |
| limit | numberdefault 5 | Optional | Maximum number of results. |
Returns
| Field | Type | Description |
|---|---|---|
| results | array | Ranked list of relevant code snippets with file paths and match scores. |
Example call
{"tool": "design_search", "arguments": {"description": "The checkout flow that shows a cart summary before payment"}}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| description | string | Required | UI or workflow description to search for in the codebase. |
Returns
| Field | Type | Description |
|---|---|---|
| matches | array | Matching components with file paths and confidence scores. |
Example call
{"tool": "resolve_frame", "arguments": {"frame": "at t.e.n.processEvent (bundle.min.js:1:43291)", "source_map_url": "https://cdn.example.com/bundle.min.js.map"}}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| frame | string | Required | Minified stack frame text to unminify. |
| source_map_url | string | Optional | URL to the source map file. If omitted, Krolik attempts to locate it automatically. |
Returns
| Field | Type | Description |
|---|---|---|
| original_frame | string | Resolved original file path, line number, and function name. |
Example call
{"tool": "site_analyze", "arguments": {"url": "https://example.com"}}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| url | string | Required | Root URL of the site to analyze. |
Returns
| Field | Type | Description |
|---|---|---|
| tech_stack | array | Detected technologies (framework, CDN, analytics). |
| seo_issues | array | List of SEO issues found with severity ratings. |
Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| url | string | Required | Starting URL for the BFS crawl. |
| depth | numberdefault 2 | Optional | Maximum crawl depth from the starting URL. |
Returns
| Field | Type | Description |
|---|---|---|
| pages | array | Crawled URLs with HTTP status codes and link counts. |
Returns
| Field | Type | Description |
|---|---|---|
| drift | array | List of services where the pinned version differs from the deployed version. |
Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| query | string | Required | Natural language query to find matching repositories. |
| limit | numberdefault 5 | Optional | Maximum number of repositories to return. |
Returns
| Field | Type | Description |
|---|---|---|
| repositories | array | Ranked list of repository URLs with star counts and descriptions. |
Example call
{"tool": "review_delta", "arguments": {"diff": "--- a/auth.go\n+++ b/auth.go\n@@ -12,7 +12,8 @@"}}Parameters
| Parameter | Type | Needed | Description |
|---|---|---|---|
| diff | string | Required | Unified diff text to analyze. |
Returns
| Field | Type | Description |
|---|---|---|
| review | object | Blast radius, risk score, and affected symbols with file paths. |
Krolik is a free, self-hosted MCP server that gives AI coding agents a persistent call graph across 16 languages. Built on the open-source Vaelor engine, it shows what breaks when a function changes, remembers past review verdicts per symbol, and traces production alerts to a file and function. It registers in Claude Code, Cursor, Windsurf, Aider and Cline.
Persistent call graph
Symbols, calls, imports and test relationships are stored in an Apache AGE property graph on PostgreSQL, so code_graph can answer questions grep cannot.
Tree-sitter parsing with typed call edges
Typed edges come from go/types for Go and bundled SCIP indexers for four further languages; everything else gets plain tree-sitter edges.
Blast radius before the edit
impact_analysis defaults to depth 5, pages direct callers, and reorders hotspots by churn; prepare_change adds a dead-code check in the same call.
Review memory per symbol
review_pr stores approve as good and request-changes as bad for each changed symbol, and understand returns the nearest learnings on later calls.
Seven-phase incident pipeline
debug_investigate joins metric spikes, Jaeger failed traces, callgraph walks, log excerpts and deployed-binary drift into ranked file:function hypotheses.
Hybrid semantic search
semantic_search blends BM25F, pgvector embeddings and one-hop graph expansion; it needs pgvector plus an embedder.
Structural rewrite and taint tracking
rewrite applies wildcard AST patterns across every supported language with a dry run, and dataflow traces tainted input to SQL and command sinks.
One endpoint for every MCP client
A single Streamable HTTP URL serves Claude Code, Cursor, Windsurf, Aider, Cline and any other MCP client.
Production incident debugging
An agent receives a Prometheus alert, calls debug_investigate, and gets ranked file:function hypotheses from metrics, failed traces and callgraph walks.
Safe refactoring
Before changing a function, agent calls impact_analysis with depth 10 to see every direct and transitive caller across the entire codebase.
Security taint tracking
Agent calls dataflow_analyze to trace unescaped user inputs through the IL/CFG and identify potential injection points before they reach production.
Codebase-wide AST rewriting
Agent calls rewrite with a tree-sitter pattern to replace a deprecated API across all 16 supported languages in one pass.
Automated PR review
Before approving a pull request, the agent calls review_pr to see which symbols and tests it touches, and the verdict is stored for next time.
The nearest AI agent skills on Hokai for the same job.
| Skill | Works with | Connects by | Checked |
|---|---|---|---|
| Claude · Cursor · Windsurf | MCP | 21 Oct | |
| Godot AILets agents build scenes, edit scripts and run games in a live Godot editor | Claude · Codex · Cursor · Gemini +1 | MCP | 15 Nov |
| Claude · Codex · Cursor | Skill file | 11 Nov | |
| Claude · Codex · Cursor · Gemini | Skill file | 11 Nov |
Nothing for the software. The vendor sells no plan or subscription, so there is nothing to buy. You cover your own hosting and, for the LLM-backed tools, whichever OpenAI-compatible endpoint you connect. The agent client you attach it to bills separately.
Yes, commercial use included. The engine and its two optional Rust companions, ox-embed-server and ox-codes, are open source and nothing is feature-gated. The limits are operational: code_graph needs PostgreSQL with Apache AGE, and semantic_search needs pgvector plus an embedder.
Sourcegraph suits people searching code across an organisation, with no graph database to run. Greptile and CodeRabbit are hosted reviewers, the better choice if you only want pull request feedback. Vaelor's own FAQ says Cursor's built-in index serves only Cursor, so Krolik makes sense when several agents need one shared endpoint.
They solve different jobs. Sourcegraph is a code search product for humans, while Krolik exposes call graphs, blast radius and review memory to agents over MCP, and you host it. Pick Sourcegraph if developers do the searching and you want zero operations, and pick Krolik if the reader is an AI agent and the code must stay on your infrastructure.
Vaelor's site quotes five minutes: docker build, docker run pointed at your LLM endpoint, then register http://127.0.0.1:8897/mcp in your MCP client. Allow longer for code_graph, which needs PostgreSQL with Apache AGE, or semantic_search, which needs pgvector and an embedder. The first understand or call_trace call on a GitHub repo indexes it, which takes a few seconds.
Krolik is a self-hosted MCP server that indexes a codebase into a call graph, so an AI coding agent can see what a change will break before it edits anything. The open-source engine underneath is published as Vaelor: the GitHub repository was renamed from go-code to vaelor, is open source, and showed 1,422 commits and 5 stars when we read it on 21 October 2026. Krolik is the name on krolik.tools, and the README calls Vaelor "the open-source engine behind Krolik".
Tree-sitter parses sixteen languages according to vaelor.ai: Go, Python, TypeScript and JavaScript, Rust, Java, C, C++, Ruby, C#, PHP, Svelte, Astro, Vue, Kotlin, Swift and HTML. Call resolution is type-aware on Go through go/types and, through bundled SCIP indexers, on TypeScript, JavaScript, Python, Java and Rust; other languages fall back to tree-sitter call edges. With PostgreSQL and Apache AGE attached, symbols, calls, imports and test relationships persist as a property graph that code_graph queries in plain English. Adding pgvector and an embedder switches on semantic_search, which blends BM25F, vector search and one-hop graph expansion.
Vaelor's site advertises 35+ MCP tools over Streamable HTTP on one local port, while krolik.tools still lists 28, so run tools/list on your own instance to see the real set. The headline tools are impact_analysis and prepare_change for blast radius, call_trace for callers and callees, review_pr, which stores a verdict per changed symbol that understand returns on later calls, dataflow for taint tracking, rewrite for AST search and replace, and debug_investigate, a seven-phase pipeline from a Prometheus alert and Jaeger traces to a ranked file:function list. One URL registers it in Claude Code, Cursor, Windsurf, Aider and Cline.
Krolik is the wrong pick for some teams. Sourcegraph is built for people searching an organisation's code and needs no graph database, and hosted reviewers such as Greptile and CodeRabbit review pull requests without you operating Postgres or an embedder. Krolik asks you to run those pieces yourself, its documentation is a README plus a small docs site, and 5 GitHub stars means few people have shared setup notes. See the wider field in our AI coding assistants guide and the AI code review roundup, or let Smart Match shortlist for your stack.
Protocol, authentication, permissions and the call contracts on this page are read from Anatoly Koptev's own documentation. The verdict is Hokai's reading of them, not the maintainer's claim.