Agenttune vs Lm
A side-by-side look at the Agenttune 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 Agenttune for conversational ai work over a hosted endpoint; 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 Agenttune when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a remote HTTP/SSE transport.
- You want tools like
get_free_tools, list_tunings, get_tuning.
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 | Conversational AI | Conversational AI |
| Quality signal | 57/100 · Good | 61/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | 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 | 0 | 121 |
| Directory activity | 0 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 6 | 8 |
| Full listing | View Agenttune | View Lm |
Tools & capabilities
Agenttune tools 6
get_free_toolsReturn the free browser tools catalog, destination registry, and local JavaScript API documentation. No personal data is accepted. Download the functions to process instructions locally; this call does not run models or install preferences.list_tuningsCatalog of all 43 AgentTune personality tuning files (slug, code, name, one-line blurb), optionally filtered by system. Use it to resolve a user's personality type to the right slug before calling get_tuning.get_tuningFetch one tuning file as Markdown with YAML front-matter. The front-matter links to the shared platform registry and installation protocol. structuredContent.body is the preference text; metadata stays separate. Confirmation of saved text is distinct from evaluation of behavior. MIT licensed.get_test_specFetch a complete questionnaire specification for mbti (32 items), enneagram (36), disc (16), attachment (36) or big-five (50). All five are available, with exact instrument/version IDs, response anchors and strict scoring instructions. The first four preserve the legacy AgentTune adaptations; instrument-specific source terms apply. Administer only when requested, keep responses local, preserve ties, and let users review any suggested communication preferences before installation.list_resourcesSearch the versioned catalog of setup guides, templates, protocols and research. Returns canonical URLs, Markdown URLs, revisions and evidence status.get_resourceRetrieve one page-specific Markdown resource by the exact ID from list_resources; includes provenance and evidence status.
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.
Agenttune
{
"mcpServers": {
"agenttune": {
"url": "https://agent-tune.com/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
Agenttune is categorized under Conversational AI and uses a remote HTTP/SSE transport. Lm belongs to Conversational AI and uses a local stdio subprocess. Pick Agenttune for conversational ai 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.
Agenttune has no declared pricing — check the project's own site. 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 agenttune and lm as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Agenttune has a quality signal of 57/100 (Good) with 0 views, 0 installs and 0 GitHub stars. Lm has 61/100 (Good) with 0 views, 0 installs and 121 GitHub stars.