mcp server

socraticode

MCP server for local codebase indexing, semantic search, and code dependency graphs.

Description as published by the maintainer. Source

• version 1.0.1
• active
• retrieval

active — Most recent push to the repository was 2026-08-05. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

21 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

codebase_about

Display information about SocratiCode — what it is, its tools and how to use it. Use this to get a quick overview of the MCP tools and their purpose.

codebase_context(projectPath)

List all context artifacts defined in .socraticodecontextartifacts.json — database schemas, API specs, infra configs, architecture docs, etc. Shows each artifact's name, description, path, and index status. Use this to discover what project knowledge is available beyond source code.

codebase_context_index(projectPath)

Index or re-index all context artifacts defined in .socraticodecontextartifacts.json. Chunks and embeds artifact content into the vector database for semantic search. Usually not needed — codebase_context_search auto-indexes on first use.

codebase_context_remove(projectPath)

Remove all indexed context artifacts for a project from the vector database. Blocked while indexing is in progress — use codebase_stop or wait for the operation to finish first. Required: projectPath.

codebase_context_search(limit, query, minScore, projectPath, artifactName)

Semantic search across context artifacts (database schemas, API specs, infra configs, etc.) defined in .socraticodecontextartifacts.json. Auto-indexes on first use and auto-detects stale artifacts. Use this to find relevant infrastructure or domain knowledge. Required: query.

codebase_graph_build(projectPath, extraExtensions)

Build a dependency graph of the codebase using static analysis (ast-grep). Maps import/require/export relationships between files. Runs in the background — call codebase_graph_status to poll progress until complete.

codebase_graph_circular(projectPath)

Find circular dependencies in the codebase.

codebase_graph_query(filePath, projectPath)

Query the code dependency graph for a specific file. Returns what the file imports and what files depend on it. Required: filePath.

codebase_graph_remove(projectPath)

Remove a project's persisted code graph. Waits for any in-flight graph build to finish first. The graph can be rebuilt with codebase_graph_build or will be rebuilt automatically on the next codebase_index. Required: projectPath.

codebase_graph_stats(projectPath)

Get statistics about the code dependency graph: total files, edges, most connected files, orphan files, circular dependencies.

codebase_graph_status(projectPath)

Check the status of the code dependency graph: build progress (if building), node/edge count, when it was last built, whether it's cached in memory. Use this to poll progress after calling codebase_graph_build.

codebase_graph_visualize(projectPath)

Generate a visual Mermaid diagram of the code dependency graph, color-coded by language with circular dependencies highlighted.

codebase_health

Check the health of all infrastructure: Docker, Qdrant container, Ollama, and embedding model. Use this to diagnose setup issues.

codebase_index(projectPath, extraExtensions)

Start indexing a codebase in the background. Returns immediately. Call codebase_status to poll progress until 100%. Do NOT search until indexing is complete. If already indexing, returns current progress.

codebase_list_projects

List all projects that have been indexed (have collections in Qdrant).

codebase_remove(projectPath)

Remove a project's codebase index entirely from the vector database. Safely stops the file watcher, cancels any in-progress indexing/update (with drain), and waits for any in-flight graph build before deleting. Required: projectPath.

codebase_search(limit, query, minScore, fileFilter, projectPath, languageFilter)

Semantic search across an indexed codebase. Only use after codebase_index is complete (check codebase_status first). Returns relevant code chunks matching a natural language query. Required: query.

codebase_status(projectPath)

Check index status: chunk count, indexing progress (%), last completed operation, file watcher state. Call after codebase_index to poll until 100% complete.

codebase_stop(projectPath)

Gracefully stop an in-progress indexing operation. The current batch will finish and checkpoint, preserving all progress. Re-run codebase_index to resume from where it left off.

codebase_update(projectPath, extraExtensions)

Incrementally update an existing codebase index. Only re-indexes changed files. Runs synchronously. Usually not needed if file watcher is active.

codebase_watch(action, projectPath)

Start/stop watching a project directory for file changes and automatically update the index. When starting, first runs an incremental update to catch any changes made since the last session, then keeps the index up to date via debounced file system watching. Required: action.

Last successful function declaration observed on 2026-08-13. Source: pkg:npm/socraticode. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: pkg:npm/socraticode.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/giancarloerra/socraticode
• npm: socraticode

Related, by what their authors tagged them

• com.knitli/codeweaver — archived, last commit 2026-06-16, shares openai, qdrant, vector-search
  Semantic code search built for AI agents. Hybrid, AST-aware, context for 166 languages.
• io.github.billy12151/memory-arbiter-mcp — last commit 2026-08-06, shares context-engine
  Shared memory store for AI coding tools with dual-timeline conflict arbitration.
• io.github.egoughnour/code-firewall-mcp — last commit 2026-01-19, shares ast, embeddings, vector-database
  Structural similarity-based code filter. Stops malicious code pattern reaching execution tools.
• RemembrallMCP — last commit 2026-07-28, shares code-graph, semantic-search
  Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.
• io.github.HaseebKhalid1507/velocirag — last commit 2026-04-05, shares embeddings, semantic-search, vector-database
  Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search.
• GitHits — last commit 2026-08-06, shares code-graph
  Search public open-source code, documentation, metadata, vulnerabilities, changelogs, and examples.
• com.kage-core/kage — last commit 2026-07-28, shares code-graph
  Verified memory for coding agents: claims cited against code, stale withheld, savings receipts.
• com.shiftinbits/constellation — last commit 2026-06-22, shares code-graph
  Code Intelligence Platform for AI Coding Agents
• io.github.blackwell-systems/knowing — last commit 2026-07-08, shares code-graph
  Content-addressed code graph with 22 MCP tools for AI agents.
• io.github.cdeust/automatised-pipeline — last commit 2026-08-04, shares code-graph
  Codebase intelligence MCP server — index any repo into a property graph; 26 tools for agents.

These share tags the maintainers applied themselves, such as openai, qdrant, vector-search, context-engine. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: ai, ai-assistant, ast, claude, claude-code, code-graph, codebase-intelligence, context-engine, docker, embeddings, gemini, gemini-cli-extension, mcp, openai, qdrant, semantic, semantic-search, vector-database, vector-embeddings, vector-search.