Lm vs Replicate
A side-by-side look at the Lm and Replicate MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Lm for conversational ai work as a local process; choose Replicate 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 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.
Choose Replicate when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
PLATFORM_REPLICATE_KEY. - You want tools like
list_models, model, model_versions.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Conversational AI | Conversational AI |
| Quality signal | 61/100 · Good | 56/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | HOUTINI_LM_ENDPOINT_URLHOUTINI_LM_API_KEYHOUTINI_LM_MODELHOUTINI_LM_SERIALISE | PLATFORM_REPLICATE_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 121 | 0 |
| Directory activity | 0 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 8 | 16 |
| Full listing | View Lm | View Replicate |
Tools & capabilities
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.
Replicate tools 16
list_modelsList all public models available on Replicate, paginated via cursor; returns owner, name, description, run count, and latest version id for each model.modelFetch metadata for a specific Replicate model by owner and name, including description, visibility, run count, latest version, and GitHub URL.model_versionsList all published versions of a Replicate model by owner and name; returns version ids, creation timestamps, and input/output schema for each version.model_versionFetch full metadata for a specific Replicate model version by owner, name, and version_id, including the complete input/output OpenAPI schema and Cog version.search_modelsSearch public Replicate models by keyword query; returns matching models with owner, name, description, and run count.collectionsList all curated Replicate model collections (e.g. "text-to-image", "speech-to-text"); returns collection slug, name, and description.collectionFetch models belonging to a specific Replicate collection by slug (e.g. "text-to-image"); returns the collection description and a list of model objects.create_predictionStart a Replicate model run by submitting a version id and input object; returns a prediction id and status that can be polled with the prediction tool until output is ready.predictionPoll the status and retrieve output for a Replicate prediction by id; returns status (starting/processing/succeeded/failed/canceled), output URLs, and logs.list_predictionsList your recent Replicate predictions in reverse chronological order, paginated via cursor; returns prediction id, model version, status, and creation timestamp.cancel_predictionCancel a prediction.list_deploymentsList your Replicate model deployments (dedicated, auto-scaled endpoints), paginated via cursor; returns owner, name, current model version, and scaling config.- +4 more on the listing page
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.
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"
}
}
}
}
Replicate
{
"mcpServers": {
"replicate": {
"command": "npx",
"args": [
"-y",
"@pipeworx/mcp-replicate"
],
"env": {
"PLATFORM_REPLICATE_KEY": "YOUR_PLATFORM_REPLICATE_KEY_HERE"
}
}
}
}
Frequently asked questions
Lm is categorized under Conversational AI and uses a local stdio subprocess. Replicate belongs to Conversational AI and uses a local stdio subprocess. Pick Lm for conversational ai work and Replicate 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.
Lm has no declared pricing — check the project's own site. Replicate 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 lm and replicate as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Lm has a quality signal of 61/100 (Good) with 0 views, 0 installs and 121 GitHub stars. Replicate has 56/100 (Good) with 1 views, 0 installs and 0 GitHub stars.