Srclight MCP sunucusu

Srclight

Deep code indexing for AI agents. SQLite FTS5 + tree-sitter + embeddings + MCP.

Srclight builds a rich, searchable index of your codebase that AI coding agents can query instantly — replacing dozens of grep/glob calls with precise, structured lookups. It is the most comprehensive code intelligence MCP server available: 42 tools covering symbol search, relationship graphs, community detection, impact analysis, git change intelligence, semantic search, build system awareness, and document extraction — capabilities no other single MCP server combines. Fully local and private: your code never leaves your machine.

Why?

AI coding agents (Claude Code, Cursor, etc.) spend 40-60% of their tokens on orientation — searching for files, reading code to understand structure, hunting for callers and callees. Srclight eliminates this waste.

Without Srclight	With Srclight
8-12 grep rounds to find callers	get_callers("lookup") — one call
Read 5 files to understand module	codebase_map() — instant overview
"Find code that does X" → 20 greps	semantic_search("dictionary lookup") — one call
Edit a function, break 47 callers	detect_changes() — shows blast radius before you commit
15-25 tool calls per bug fix	5-8 tool calls per bug fix

Features

• Minimal dependencies — single SQLite file per repo, no Docker/Redis/vector DB
• Fully offline — no API calls, works air-gapped (Ollama local embeddings)
• Incremental — only re-indexes changed files (content hash detection)
• 19 languages — Python, C, C++, C#, Java, Kotlin, Swift, Dart, Go, Rust, JavaScript, TypeScript, PHP, Lua, Bash, SQL, Groovy, CMake, Markdown — include fragments (.inc, .inl, .ipp, .tcc) included, plus any extension you declare with --ext
• Says what it skipped — index_status names the extensions a run walked past, so an incomplete answer never reads as a complete one
• 10 document formats — PDF, DOCX, XLSX, HTML, CSV/TSV, email (.eml), images (PNG/JPG/SVG/etc.), plain text, RST, Markdown
• Optional OCR — PaddleOCR for scanned/image-only PDF pages; pytesseract for images
• 4 search modes — symbol names, source code (trigram), documentation (stemmed), semantic (embeddings)
• Hybrid search — RRF fusion of keyword + semantic results for best accuracy
• Multi-repo workspaces — search across all your repos simultaneously via SQLite ATTACH+UNION
• MCP server — works with Claude Code, Cursor, and any MCP client
• CLI — index, search, and inspect from the terminal
• Auto-reindex — git post-commit/post-checkout hooks keep indexes fresh

MCP argument validation

Srclight's MCP server refuses unknown tool arguments instead of silently dropping them — a mistyped filter like projects= (for project=) is rejected with an error, never answered as if the constraint were applied. Every tool advertises additionalProperties: false. The guard is the shared mcpkit policy, vendored as one hash-verified file (src/srclight/_mcpkit.py).

AI agents: if a call returns unknown argument(s): … running older code than you think … reconnect, the running server predates the argument you sent (a long-lived daemon serves the code it launched with). Nothing ran — check the reported revision and reconnect the MCP; don't retry the same call.

Index freshness

Every symbol/graph result carries index_freshness: the short string "verified-fresh" when the files behind the answer are byte-identical to what was indexed, or a bounded object naming which files are stale, missing, or not indexed. check_freshness(paths?) probes any paths — or the whole index — on demand (unchanged files cost one stat each; never writes), and index_status reports whole-index checked/stale_count.

AI agents: a result stamped stale describes the code as indexed, not as it is now — reindex (srclight index) or read the live file before acting on line numbers or bodies from it. "verified-fresh" is the affirmative signal; its absence on a workspace-mode result means freshness was not checkable for that result, never that it is fresh.

Index coverage

index_status reports both sides of what an index holds: indexed_extensions, every suffix it reads, and unindexed_extensions, the {extension: file count} this repo holds that the last run walked past, plus oversize_skipped for files refused on size and failed_files for files that could not be read or parsed. list_projects carries the same per project, and find_pattern attaches the tally plus a note whenever it is non-empty.

A gap means code that was never read, so the tally deliberately leaves out what is skipped on purpose: ignored paths (binaries, vendored trees, .git) in both the git ls-files and directory-walk modes, and inert suffixes — config, data and manifests (.json, .toml, .yml, .lock, …) along with suffixless files like LICENSE or Dockerfile. Every repo carries some of those; counting them would leave the tally non-empty everywhere, put the warning on every result and bury the extensions that genuinely hold unread code. A document format this install cannot read for want of an extra (.pdf, .docx, .xlsx, .html) IS counted — it is unread, and one pip install away from being read. So is a source extension the ignore list blocks anyway (*.cmake sits next to the build artefacts while cmake is a language srclight parses), and a language whose tree-sitter grammar is not installed — indexing those files would record them as read while they hold no searchable symbol.

truncated on a find_pattern result means the page was cut short, and nothing else. It has never described scan coverage: the search runs over indexed symbols, so files the indexer never read cannot appear whatever it says. A gap is now readable from the index instead of being discoverable only by comparing a result to a grep.

Include fragments (.inc, .inl, .ipp, .tcc) — the files a project uses to split an oversized translation unit, included at file scope and holding real definitions — are indexed as source. .inc names an include convention rather than a language, so its content decides: PHP, C++, else C.

For a house extension srclight does not know, declare it once:

srclight index --ext .zz=cpp          # repeatable; --ext none clears
srclight index --ext .inc=skip        # or: leave an extension unread

skip is the way out of the .inc sniff for a project that uses it for Makefile or SQL fragments: those files then count as a declared gap rather than being parsed as C.

The declaration is stored in the index, not the command line, so the git hooks' flag-less reindexes keep reading those files.

AI agents: a non-empty unindexed_extensions means the answer you are holding is not a whole-tree answer, whatever truncated says — cross-check with grep, or have the extension declared. An empty one is the affirmative signal.

Graph resolution labels

Reference edges are built by name matching plus ranked evidence, and every caller/callee edge carries a resolution label saying how its target was chosen: same_file (the caller's own file defines the name), unique_file (all same-named candidates live in one file), import (the caller's imports single out one file), same_dir, or name_only. Names appearing only in comments or strings never become edges.

AI agents: name_only means a ranked candidate list across same-named symbols — read it as "one of these", not a confirmed link; verify with get_symbol or a reference search before acting on it. The stronger labels are safe to treat as resolved.

Requirements

• Python 3.11+
• Git (for change intelligence and auto-reindex hooks)
• Ollama (optional, for semantic search / embeddings) — ollama.com
• NVIDIA GPU + cupy (optional, for GPU-accelerated vector search)
• Poppler (optional, for PaddleOCR scanned-PDF support) — apt install poppler-utils / brew install poppler

Quick Start

# Install from PyPI
pip install srclight

# Install from source
git clone https://github.com/srclight/srclight.git
cd srclight
pip install -e .

# Optional: document format support (PDF, DOCX, XLSX, HTML, images)
pip install 'srclight[docs,pdf]'

# Optional: OCR for scanned PDFs (also needs poppler-utils on your system)
pip install 'srclight[pdf,paddleocr]'

# Optional: OCR for images (needs tesseract on your system)
pip install 'srclight[docs,ocr]'

# Optional: GPU-accelerated vector search (requires CUDA 12.x)
pip install 'srclight[gpu]'

# Everything (docs + pdf + ocr + paddleocr + gpu)
pip install 'srclight[all]'

# Index your project
cd /path/to/your/project
srclight index

# Index with embeddings (requires Ollama running)
srclight index --embed qwen3-embedding

# Read an extra extension as a known language (recorded in the index)
srclight index --ext .inc=cpp

# Search
srclight search "lookup"
srclight search --kind function "parse"
srclight symbols src/main.py

# Start MCP server (for Claude Code / Cursor)
srclight serve

Note: srclight index keeps .srclight/ out of git through the repo's local .git/info/exclude (it never edits your tracked .gitignore). Index databases and embedding files can be large and should never be committed.

Running tools from the shell

Every MCP tool is reachable from the CLI, which is how an agent with a sandbox can query the index without the answer ever entering its context:

srclight tool --list                    # every tool and what it does
srclight tool find_pattern --help       # arguments, from the tool's own schema
srclight tool find_pattern --pattern 'this->timer' --kind function --limit 80

Output is the tool's JSON on stdout and nothing else, so it pipes. Exit codes are 0 on success, 1 when the tool reports an error, 2 on a usage error — a usage error writes nothing to stdout and says why on stderr.

The command reads the server's own tool registry, so it always matches the tools your MCP client sees — and a tool renamed on the MCP side is renamed here too.

Semantic Search (Embeddings)

Srclight supports embedding-based semantic search for natural language queries like "find code that handles authentication" or "where is the database connection pool".

Setup

# Install Ollama (https://ollama.com)
# Pull an embedding model
ollama pull qwen3-embedding       # Best quality (8B params, needs ~6GB VRAM)
ollama pull nomic-embed-text      # Lighter alternative (137M params)

# Index with embeddings
srclight index --embed qwen3-embedding

# Or index workspace with embeddings
srclight workspace index -w myworkspace --embed qwen3-embedding

Choosing the Model Once

--embed only has to be passed once per index. The index records the model and every later run reuses it — including the flag-less srclight index . the git hooks run on each commit, and the MCP reindex tool. Without that, every symbol added after the first run stays unembedded until someone remembers the flag.

srclight index --embed qwen3-embedding   # first run: records the model
srclight index                           # later runs: reuse it, no flag

The recorded name is provider-qualified, so the second run reports Embedding model: ollama:qwen3-embedding (from the existing index).

For indexes that have no model recorded yet, SRCLIGHT_EMBED_MODEL supplies one:

export SRCLIGHT_EMBED_MODEL=qwen3-embedding
srclight index                           # a fresh index embeds with it

Resolution order is --embed > the model recorded in the index > SRCLIGHT_EMBED_MODEL. The variable comes last on purpose: it is a default for new indexes, never an override. Ahead of the recorded model, exporting it once would make the next commit in an unrelated repo re-embed every symbol it holds, silently, from a background hook. Switching an existing index stays an explicit --embed.

Two escape hatches:

srclight index --no-embed             # skip embedding for this run only
srclight index --forget-embed-model   # stop embedding this index for good

--forget-embed-model is the off switch for the hooks, whose command line is fixed: after it, commits index without ever calling the embedding model, until you pass --embed again. Over MCP, reindex(embed=False) is the per-call equivalent of --no-embed.

Note that skipping is not free. Reindexing a changed file drops the embeddings of the symbols it replaces, and a skipped pass does not put them back — semantic coverage decays on exactly the files being edited. Ask embedding_status() what an index will do: configured_model is the model the next flag-less run resolves to — the whole chain, environment variable included — and null means it will not embed. Single-repo mode only: in a workspace each project records its own, so the field is not reported.

How It Works

1. Each symbol's name + signature + docstring + content is embedded as a float vector
2. Vectors are stored as BLOBs in symbol_embeddings table (SQLite)
3. After indexing, a .npy sidecar snapshot is built and loaded to GPU VRAM (cupy) or CPU RAM (numpy) for fast search
4. semantic_search(query) embeds the query and runs cosine similarity against the GPU-resident matrix (~3ms for 27K vectors on a modern GPU)
5. hybrid_search(query) combines FTS5 keyword results + embedding results via Reciprocal Rank Fusion (RRF)

Embedding Providers

Provider	Model	Quality	Local?	Notes
Ollama (default)	qwen3-embedding	Best local	Yes	Needs ~6GB VRAM
Ollama	nomic-embed-text	Good	Yes	Lighter, works on 8GB VRAM
Voyage AI (API)	voyage-code-3	Best overall	No	Requires VOYAGE_API_KEY

# Use Voyage Code 3 (API, highest quality)
VOYAGE_API_KEY=your-key srclight index --embed voyage-code-3

Storage

Embeddings are stored in symbol_embeddings table in .srclight/index.db. After indexing, a .npy sidecar snapshot is built for fast GPU loading:

File	Purpose
index.db	Write path — per-symbol CRUD during indexing
embeddings.npy	Read path — contiguous float32 matrix for GPU/CPU search
embeddings_norms.npy	Pre-computed row norms (avoids recomputation per query)
embeddings_meta.json	Symbol ID mapping, model info, version for cache invalidation

For ~27K symbols at 4096 dims (qwen3-embedding), that's ~428 MB on disk, ~450 MB in VRAM. Incremental: only re-embeds symbols whose content changed; sidecar rebuilt after each indexing run.

Multi-Repo Workspaces

Search across multiple repos simultaneously. Each repo keeps its own .srclight/index.db; at query time, srclight ATTACHes them all and UNIONs across schemas.

# Create a workspace
srclight workspace init myworkspace

# Add repos
srclight workspace add /path/to/repo1 -w myworkspace
srclight workspace add /path/to/repo2 -w myworkspace -n custom-name

# Index all repos (with optional embeddings)
srclight workspace index -w myworkspace
srclight workspace index -w myworkspace --embed qwen3-embedding

# Search across all repos
srclight workspace search "Dictionary" -w myworkspace
srclight workspace search "Dictionary" -w myworkspace --project repo1

# Status
srclight workspace status -w myworkspace
srclight workspace list

# Start MCP server in workspace mode
srclight serve --workspace myworkspace

Git submodules are not indexed automatically — git ls-files does not recurse into them. To index a submodule, clone it separately and add it as its own workspace project. See docs/usage-guide.md for details.

MCP Integration

Srclight supports two transport modes: stdio (one server per session) and SSE (persistent server, multiple sessions). SSE is recommended for workspaces.

Claude Code

Stdio (simplest — one server per session):

# Single repo
claude mcp add srclight -- srclight serve

# Workspace mode
claude mcp add srclight -- srclight serve --workspace myworkspace

# Make it available in all projects (user scope)
claude mcp add --scope user srclight -- srclight serve --workspace myworkspace

SSE (persistent server — recommended for workspaces):

Run srclight as a long-lived server, then point Claude Code at it:

# Start the server (default: http://127.0.0.1:8742/sse)
srclight serve --workspace myworkspace &

# Or install as a systemd user service (Linux/WSL)
# See docs/usage-guide.md for the service file

# Connect Claude Code to the running server
claude mcp add --transport sse srclight http://127.0.0.1:8742/sse

SSE mode supports multiple concurrent sessions and survives Claude Code restarts.

Cursor

SSE (recommended): Run srclight once, then connect Cursor to it. Best for responsiveness and no cold-start per session.

Start the server: srclight serve --workspace myworkspace (default SSE on port 8742).

• UI: Settings → Tools & MCP → Add new MCP server → Type: streamableHttp, URL: http://127.0.0.1:8742/sse.
• JSON (project .cursor/mcp.json or global ~/.cursor/mcp.json):

"srclight": {
  "url": "http://127.0.0.1:8742/sse"
}

Stdio (alternative): One server process per Cursor session.

• UI: Type: command, Command: srclight, Args: serve --workspace myworkspace (or serve for single-repo).
• JSON:

"srclight": {
  "command": "srclight",
  "args": ["serve", "--workspace", "myworkspace"]
}

For single-repo: "args": ["serve"]. Restart Cursor completely after adding the server.

Verify: In Cursor chat, ask "What projects are in the srclight workspace?" or "List srclight tools" — the agent should call list_projects() or show srclight tools.

OpenClaw

OpenClaw connects to srclight via mcporter, its built-in MCP tool server CLI.

# 1. Add srclight to mcporter's home config
mcporter config add srclight http://127.0.0.1:8742/sse \
  --transport sse --scope home \
  --description "Srclight deep code indexing"

# 2. Verify the connection
mcporter call srclight.list_projects

# 3. Restart the OpenClaw gateway to pick up the new server
systemctl --user restart openclaw-gateway  # if using systemd
# or: openclaw daemon restart

The OpenClaw agent can then use srclight tools via the mcporter skill:

mcporter call srclight.search_symbols query="my_function"
mcporter call srclight.get_callers symbol_name="MyClass" project="my-repo"
mcporter call srclight.hybrid_search query="authentication logic"

Prerequisite: Srclight must be running as an SSE server (see above). OpenClaw's mcporter connects over HTTP — stdio mode is not supported.

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "srclight": {
      "command": "srclight",
      "args": ["serve", "--workspace", "myworkspace"]
    }
  }
}

Any MCP Client (SSE)

Any MCP-compatible client can connect to the SSE endpoint:

http://127.0.0.1:8742/sse

MCP Tools (43)

Srclight exposes 43 MCP tools organized in eight tiers. The MCP server includes built-in instructions that guide AI agents on which tool to use and when — agents receive a session protocol, tool selection guide, and project parameter documentation automatically on connection.

Tier 1: Instant Orientation

Tool	What it does
codebase_map()	Full project overview — call first every session
search_symbols(query)	Keyword (FTS5) search across symbol names, code, and docs
get_symbol(name)	Full source code + metadata for a symbol
get_signature(name)	Just the signature (lightweight)
symbols_in_file(path)	Table of contents for a file
find_pattern(pattern, limit, offset)	Regex search inside symbol bodies; says when it truncated
list_projects()	All projects in workspace with stats

Tier 2: Relationship Graph

Tool	What it does
get_callers(name)	Who calls this symbol?
get_callees(name)	What does this symbol call?
get_dependents(name, transitive)	Blast radius — what breaks if I change this?
get_implementors(interface)	All classes implementing an interface
get_tests_for(name)	Test functions covering a symbol
get_type_hierarchy(name)	Inheritance tree (base classes + subclasses)
find_imports(path)	Import statements in a file, resolved to indexed files
find_dead_code(kind)	Symbols nothing calls or references

Tier 2b: Community & Impact Analysis

Tool	What it does
get_communities(project)	Auto-detected functional module clusters (Louvain algorithm)
get_community(name, project)	Which community a symbol belongs to, with all co-members
get_execution_flows(project)	Traced execution paths from entry points through the call graph
get_impact(name, project)	Blast radius + risk level (LOW / MEDIUM / HIGH / CRITICAL)
detect_changes(project, ref?)	Map git diff to affected symbols — aggregate blast radius of your edits

Tier 3: Git Change Intelligence

Tool	What it does
blame_symbol(name)	Who changed this, when, and why
recent_changes(n)	Commit feed (cross-project in workspace)
git_hotspots(n, since)	Most frequently changed files (bug magnets)
whats_changed()	Uncommitted work in progress
changes_to(name)	Commit history for a symbol's file

Tier 4: Build & Config

Tool	What it does
get_build_targets()	CMake/.csproj/npm targets with dependencies
get_platform_variants(name)	#ifdef platform guards around a symbol
platform_conditionals()	All platform-conditional code blocks

Tier 5: Semantic Search (Embeddings)

Tool	What it does
semantic_search(query)	Find code by meaning (natural language)
hybrid_search(query)	Best of both: keyword + semantic with RRF fusion
embedding_status()	Embedding coverage and model info

Tier 6: Meta & Server

Tool	What it does
index_status()	Index freshness and stats
check_freshness(paths)	Is the index current for these files, or for all of them?
show_status(message)	Show the srclight dashboard window and return current status
reindex(embed=True)	Trigger incremental re-index; embed=False skips the embedding pass (and lets semantic coverage decay)
embedding_health()	Check if the embedding provider (Ollama, etc.) is reachable
setup_guide()	Structured setup instructions for agents and users
server_stats()	Server uptime and process info
restart_server()	Request server restart (SSE only)