lineai-mcp-server

An MCP Server to utilize Lineai's rich software dependency data in your AI programming assistant.

Documentation

Code-derived architecture documentation lives in docs/ (added in LIN-737; updated for the LIN-699 changes — PR #61 / neo4cape #1860):

• docs/architecture.md — full architecture analysis: module map, tool surface and the Lineai /api/... endpoints each tool calls, auth flow, caching, error-handling taxonomy, configuration, packaging/release, and findings.
• docs/architecture-diagrams.md — Mermaid diagram set (ecosystem, module map, call sequence, auth/caching, error taxonomy).
• docs/rendered-diagrams/ — committed SVG renders of every diagram.

Components

Tools

The server implements eight tools: two impact tools plus six graph tools backed by the Lineai graph HTTP API.

Code Analysis Tools

• lineai-method-impact: Pulls an impact assessment from the Lineai server's APIs for your code.
  • Takes the given "method" that you're working on. Pass the fully-qualified class name in "class" (e.g. com.acme.shell.AnalyzeCommands) when the simple name may exist in several repositories: a fully-qualified class selects exactly that class, while a simple name that matches several classes returns an ambiguity page listing the candidates instead of silently analyzing another repository's class.
  • The impact is a bounded upstream traversal from the Lineai graph impact endpoint (depth argument, default 3, max 10). The report's Impact scope section says where the data came from (graph, or the legacy full-chain endpoint when the graph endpoint is not deployed) and whether it is complete (ok) or a lower bound (partial) — a partial result is never "no impact".
• lineai-database-impact: Analyzes impacts between code and database entities.
  • Takes the database entity type (column, table, or view) and its name.

All eight tools also accept optional workspace and materialized_view_id arguments to scope a single call; when neither is given (and LINEAI_WORKSPACE_NAME is unset) the server's default workspace's latest materialized view is used automatically.

Graph API tools

These call POST / GET endpoints under /api/ai-retrieval/graph/ on the same host as LINEAI_SERVER_HOST, using the same session auth as other MCP tools. If graph routes are not deployed, the server returns a clear “graph not available” style message (often after HTTP 404).

• lineai-graph-capabilities: GET — discover supported relationship types, limits, and flags for the workspace materialized view (materializedViewId resolved like every other tool: explicit id → workspace argument → LINEAI_WORKSPACE_NAME → server default).
• lineai-graph-search: Search nodes by text query / q and/or identity_prefix; optional scan_space (scan space id or display name), prefer_latest_scan, limit. Results are ranked by the server (exact short name → exact fully-qualified name → class-like labels → text score → newest scan) and data.hits[i] describes data.nodes[i] (score, matchKind, labelTier); data.totalHitCount is the real total, so a full page means "narrow the query", not "absent".
• lineai-graph-impact: Bounded dependency / blast-radius traversal from seed_node_ids with direction (upstream = what depends on the seeds, downstream, both) and depth (server default 3, max 10). The response carries status (ok | partial), truncated, nodeCount, staticAnalysisGap and assumptionsApplied markers; the tool prints a note above the JSON whenever the result is partial, degraded, or an older server ignored an option.
• lineai-graph-path-explain: Shortest-path style explanation between from_node_id and to_node_id.
• lineai-graph-validate-change-scope: Heuristic checklist / ris

... View full README on GitHub