Codebase Memory MCP vs Lm
A side-by-side look at the Codebase Memory MCP and Lm MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Codebase Memory MCP for knowledge & memory work as a local process; choose Lm for conversational ai as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Codebase Memory MCP when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
index_repository, search_graph, query_graph.
Choose Lm when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
HOUTINI_LM_ENDPOINT_URL, HOUTINI_LM_API_KEY, HOUTINI_LM_MODEL, HOUTINI_LM_SERIALISE. - You want tools like
chat, custom_prompt, code_task.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Knowledge & Memory | Conversational AI |
| Quality signal | 73/100 · Great | 61/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | HOUTINI_LM_ENDPOINT_URLHOUTINI_LM_API_KEYHOUTINI_LM_MODELHOUTINI_LM_SERIALISE |
| Verified owner | Community listing | Community listing |
| GitHub stars | 47,004 | 121 |
| Directory activity | 8 views 1 installs 1 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 17 | 8 |
| Full listing | View Codebase Memory MCP | View Lm |
Tools & capabilities
Codebase Memory MCP tools 17
index_repositoryIndex a repository. full/moderate add semantics; fast omits them; cross-repo-intelligence links services. Reports coverage gaps.search_graphFind symbols via BM25 query, regex name/qn filters, or semantic_query. Rows keep qn/file/lines and in/out over CALLS/USAGE/CALL_REFERENCE/INHERITS/IMPLEMENTS.query_graphRead-only Cypher for multi-hop, aggregation, complexity, or cross-service analysis. Default: 200 visible rows with exact/lower-bound totals and truncation; continue safely with next_cursor. graph=missed is a file tree of flagged coverage gaps; absence is not proof of completeness. Use get_graph_schema(diagnostics=full) for properties.trace_pathTrace callers/callees, data flow, or cross-service paths. Defaults exclude tests and resolver evidence. Rows keep qn/hop with explicit totals, relations, and continuations.get_code_snippetRead a search_graph symbol. auto bounds source and outlines large containers; full restores up to 500 lines. Source/outline pages continue; coverage_note marks gaps.get_file_outlineDeclaration outline of one exact repository-relative file: optional exact label filter, source order, exact total/offset/limit paging; file/folder/container nodes excluded.get_graph_schemaGet node-label and edge-type counts. diagnostics=full also lists queryable properties.compare_graphsCompare two indexed snapshots: deterministic target-only additions and base-only removals of stable node/edge identities; each set capped by limit and a 512 KiB budget with exact totals and truncation reasons.get_architectureCompact counts, languages, packages, entry points. Request structure, dependencies, routes, hotspots, boundaries, layers, clusters, cycles, or file_tree; path scopes a directory.search_codeGraph-ranked text search: compact symbols, full bounded source, or file paths.list_projectsList projects with stable paging. Identity is lean; stats adds graph sizes.delete_projectDelete a project from the index- +5 more on the listing page
Lm tools 8
chatThe workhorse. Send a task, get an answer. The description includes planning triggers that nudge Claude to identify offloadable work when it's starting a big task.custom_promptThree-part prompt: system, context, instruction. Keeping them separate prevents context bleed - consistently outperforms stuffing everything into one message, especially with local models. I tested this properly one weekend - took the same batch of review tasks and ran them both ways. Splitting thi…code_taskBuilt for code analysis. Pre-configured system prompt with temperature and output constraints tuned per model family via the routing layer.code_task_filesLike `code_task`, but the local LLM reads files directly from disk — source never passes through the MCP client's context window. Use this when reviewing multiple related files, or a single large file that's awkward to paste. Files are read in parallel with `Promise.allSettled`, so one unreadable f…embedGenerate text embeddings via the OpenAI-compatible `/v1/embeddings` endpoint. Requires an embedding model to be available - Nomic Embed is a solid choice. Returns the vector, dimension count, and usage stats.discoverHealth check and speed readout. Returns model name, context window, capability profile, connection latency (labelled explicitly — this is the `/v1/models` fetch round-trip, *not* inference speed), and the active model's measured tok/s and TTFT averaged over the session. Before any real call has run…list_modelsLists everything on the LLM server - loaded and downloaded - with full metadata: architecture, quantisation, context window, capabilities, and HuggingFace enrichment data. Shows capability profiles describing what each model is best at, so Claude can make informed delegation decisions.statsCompact markdown dump of your offload stats — session and lifetime totals, per-model performance history, reasoning-token overhead — without the model catalog that `discover` prints. Cheap to call repeatedly to watch the 💰 counter climb.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Codebase Memory MCP
{
"mcpServers": {
"deusdata-codebase-memory-mcp": {
"command": "npx",
"args": [
"-y",
"codebase-memory-mcp"
]
}
}
}
Lm
{
"mcpServers": {
"lm": {
"command": "npx",
"args": [
"-y",
"@houtini/lm"
],
"env": {
"HOUTINI_LM_ENDPOINT_URL": "YOUR_HOUTINI_LM_ENDPOINT_URL_HERE",
"HOUTINI_LM_API_KEY": "YOUR_HOUTINI_LM_API_KEY_HERE",
"HOUTINI_LM_MODEL": "YOUR_HOUTINI_LM_MODEL_HERE",
"HOUTINI_LM_SERIALISE": "YOUR_HOUTINI_LM_SERIALISE_HERE"
}
}
}
}
Frequently asked questions
Codebase Memory MCP is categorized under Knowledge & Memory and uses a local stdio subprocess. Lm belongs to Conversational AI and uses a local stdio subprocess. Pick Codebase Memory MCP for knowledge & memory work and Lm for conversational ai.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Codebase Memory MCP is listed as free. Auth: no auth required. Lm has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add deusdata-codebase-memory-mcp and lm as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Codebase Memory MCP has a quality signal of 73/100 (Great) with 8 views, 1 installs and 47,004 GitHub stars. Lm has 61/100 (Good) with 0 views, 0 installs and 121 GitHub stars.