Local AI MCP
NPM · @TMHS/LOCAL-AI-MCP
Run, fit, and route work to local LLMs (Ollama, LM Studio, llama.cpp, MLX, vLLM, and more).
Available components
Last scanned (20 hours ago)
Scores higher than 61% of npm servers
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 30 of 92 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency87
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to TMHSDigital/local-ai-mcp). View diagnostics → Pass
- License check failed: the license (CC-BY-NC-ND-4.0) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 0 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability80
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 3109 tokens (~124/item across 25 items; 19 tools + 6 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management3
- Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 93% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 21 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- Stability: unverified → 0.03 ▲ functional
- 3 Nov 26 64
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Analysed npm/@tmhs/local-ai-mcp@0.6.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | TMHSDigital/local-ai-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/TMHSDigital/local-ai-mcp/.github/workflows/publish.yml@refs/heads/main |
| Rekor log index | 3674974166 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:369f43befa315338ab5f4fa4b38c63eb9c765a97fe465ebacdc9854553a4a444050f6b53cb69ad521ba2a7a01c66e7ea9ef5e47fb1d39265b8da94bcf |
Background: How many MCP packages publish verified provenance →
Dependencies 92 packages
| Packages resolved | 92 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
benchmark Benchmark ~216
HEAVY: Runs REAL inference. Measures a model on this machine with a warmup (absorbs load time) plus N streamed runs: time-to-first-token, generation tokens/sec (runtime-reported when available, else measured after the first token), and prompt-processing speed. Pass models[] to compare several models with the same prompt, ranked by generation speed.
| Name | Type | Req | Description |
|---|---|---|---|
| maxTokens | integer | – | Tokens to generate per run (default 128) |
| model | string | – | Model id/name to benchmark |
| models | array | – | Compare several models (ranked by median generation tokens/sec) |
| prompt | string | – | Prompt (default: a short fixed prompt) |
| provider | string | – | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| runs | integer | – | Measured runs per model (default 3) |
| warmup | boolean | – | Run a 1-token warmup first so load time is excluded (default true) |
| Name | Type | Req | Description |
|---|---|---|---|
| results | array | yes | – |
No examples provided.
complete Delegated completion ~386
DELEGATED INFERENCE: Offload a completion to a model you choose for cost savings and privacy. Without provider, runs on the live LOCAL provider that has the model (never a hosted API unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set); the result's 'provider', 'host' and 'local' fields say where it ran. Supports system prompts, JSON / JSON-Schema output (validated 'parsed' field), seed/topP/topK, image inputs for vision models, and contextLength for long inputs. Streams tokens via MCP progress notifications when the client sends a progressToken.
| Name | Type | Req | Description |
|---|---|---|---|
| contextLength | integer | – | Context window to run with (Ollama num_ctx). Raise it for long inputs to avoid truncation. |
| maxTokens | integer | – | Maximum tokens to generate |
| messages | array | – | Chat messages; content may be a string or text/image parts (vision models) |
| model | string | yes | Model id/name to run the completion on |
| options | object | – | Provider-specific extras passed through as-is |
| prompt | string | – | Plain prompt text (alternative to messages) |
| provider | string | – | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| repeatPenalty | number | – | – |
| responseFormat | – | – | Constrain output to JSON (json_object) or a JSON Schema (json_schema); the result includes a validated 'parsed' value |
| seed | integer | – | Seed for reproducible sampling |
| stop | array | – | Stop sequences |
| stream | boolean | – | Stream tokens (default true). Progress notifications are sent when the client provides a progressToken. |
| system | string | – | System instruction |
| temperature | number | – | Sampling temperature |
| topK | integer | – | – |
| topP | number | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| host | string | yes | – |
| local | boolean | yes | – |
| model | string | yes | – |
| parsed | – | – | – |
| provider | string | yes | – |
| text | string | yes | – |
No examples provided.
delegate Delegate a task to the best local model ~457
ONE CALL to offload work locally: pick the best model for a task on THIS machine, make it ready, and run it. Prefers models already loaded (no load cost), then installed models that fit your free VRAM, then (with allowPull) the best catalog model that fits. Task specialists (coder, vision, reasoning) win over general models; then larger fitting models win, grouped into size tiers (within ~20% parameter count); inside a tier, the model benchmarked fastest on this machine wins (run benchmark to record speeds; results expire after 14 days). Never uses a hosted provider unless allowHosted is true. Returns the completion plus a 'routing' block explaining the choice.
| Name | Type | Req | Description |
|---|---|---|---|
| allowHosted | boolean | – | Allow hosted providers (default false) |
| allowPull | boolean | – | Download a catalog model if nothing suitable is installed (default false) |
| contextLength | integer | – | Context window to run with (Ollama num_ctx). Raise it for long inputs to avoid truncation. |
| maxSizeBytes | number | – | Ignore models larger than this |
| maxTokens | integer | – | Maximum tokens to generate |
| messages | array | – | Chat messages; content may be a string or text/image parts (vision models) |
| options | object | – | Provider-specific extras passed through as-is |
| prompt | string | – | Plain prompt text (alternative to messages) |
| provider | string | – | Restrict to one provider. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| repeatPenalty | number | – | – |
| responseFormat | – | – | Constrain output to JSON (json_object) or a JSON Schema (json_schema); the result includes a validated 'parsed' value |
| seed | integer | – | Seed for reproducible sampling |
| stop | array | – | Stop sequences |
| stream | boolean | – | Stream tokens (default true). Progress notifications are sent when the client provides a progressToken. |
| system | string | – | System instruction |
| task | string | yes | What kind of work this is |
| temperature | number | – | Sampling temperature |
| topK | integer | – | – |
| topP | number | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | yes | – |
| provider | string | yes | – |
| routing | object | yes | – |
| text | string | yes | – |
No examples provided.
embed Delegated embeddings ~104
DELEGATED EMBEDDINGS: Generate embeddings for a string or an array of texts. Without provider, runs on the live local provider that has the model. Always returns one vector per input.
| Name | Type | Req | Description |
|---|---|---|---|
| input | – | yes | Text or array of texts to embed |
| model | string | yes | Embedding model id/name |
| provider | string | – | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| Name | Type | Req | Description |
|---|---|---|---|
| dimensions | number | yes | – |
| embeddings | array | yes | – |
| host | string | yes | – |
| local | boolean | yes | – |
| model | string | yes | – |
| provider | string | yes | – |
No examples provided.
ensure_model Ensure model is ready ~233
Make a model ready in one call: optionally pull it, check it fits current free VRAM, unload other models if needed (evict: 'lru' or 'all'), load it, and verify. Use dryRun:true to get the plan without changing anything.
| Name | Type | Req | Description |
|---|---|---|---|
| allowPull | boolean | – | Download the model if it is not installed (default false) |
| contextLength | integer | – | Context window to fit and load with (default 4096) |
| dryRun | boolean | – | Return the plan only (default false) |
| evict | string | – | Unload other models to make room: none (default), lru (least recently used first), all |
| keepAlive | string | – | Keep-alive for the loaded model, e.g. '30m' |
| kvCacheType | string | – | KV cache precision used for the fit estimate (default f16) |
| model | string | yes | Model id/name |
| provider | string | – | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| Name | Type | Req | Description |
|---|---|---|---|
| fit | object | – | – |
| model | string | yes | – |
| plan | array | yes | – |
| provider | string | yes | – |
| ready | boolean | yes | – |
No examples provided.
fit_check Fit check ~234
Will a model run on this machine, and where? Uses the installed model's size and exact layer architecture when the runtime exposes it (else parameter-count or catalog estimates) to size weights + KV cache for a context length, then compares with free VRAM summed across GPUs and available RAM. Returns target gpu / partial (GPU+CPU split) / cpu / none, with the numbers and how the KV estimate was made. Credits back memory the model already uses if it is loaded.
| Name | Type | Req | Description |
|---|---|---|---|
| contextLength | integer | – | Context length for the KV-cache estimate (default 4096) |
| kvCacheType | string | – | KV cache precision: f16 (default), q8_0, q4_0 |
| model | string | yes | Model id/name to check |
| parameterSize | string | – | Parameter size like "7B" (overrides lookup) |
| provider | string | – | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| sizeBytes | number | – | Explicit weight size in bytes (overrides lookup) |
| Name | Type | Req | Description |
|---|---|---|---|
| availableBytes | number | yes | – |
| fits | boolean | yes | – |
| loaded | boolean | yes | – |
| model | string | yes | – |
| note | string | yes | – |
| requiredBytes | number | yes | – |
| sizeSource | string | yes | – |
| target | string | yes | – |
No examples provided.
health_check Health check ~77
Check whether each provider is reachable and report its version (and live metrics such as vLLM KV-cache usage). Without provider, checks every configured provider, including hosted ones.
| Name | Type | Req | Description |
|---|---|---|---|
| provider | string | – | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| Name | Type | Req | Description |
|---|---|---|---|
| health | object | yes | – |
No examples provided.
list_loaded List loaded models ~66
List models currently loaded into memory on each live provider, with VRAM use and context length where the runtime reports them.
| Name | Type | Req | Description |
|---|---|---|---|
| provider | string | – | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| Name | Type | Req | Description |
|---|---|---|---|
| loaded | object | yes | – |
No examples provided.
list_models List installed models ~63
List models installed/available on each live provider, keyed by provider. Pass provider to query just one.
| Name | Type | Req | Description |
|---|---|---|---|
| provider | string | – | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| Name | Type | Req | Description |
|---|---|---|---|
| models | object | yes | – |
No examples provided.
list_providers List providers ~100
List configured model runtimes (Ollama, LM Studio, llama.cpp, Docker Model Runner, and any opt-in MLX / vLLM / Foundry Local / OpenAI-compatible / hosted instances) with host, kind (local or hosted), live status, and capabilities.
| Name | Type | Req | Description |
|---|---|---|---|
| provider | string | – | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| Name | Type | Req | Description |
|---|---|---|---|
| providers | array | yes | – |
No examples provided.
load_model Load model ~148
Load a model into memory on ONE provider so it is ready for inference. Optional keepAlive (e.g. '5m', '1h') and contextLength. Without provider, uses the live local provider that has the model.
| Name | Type | Req | Description |
|---|---|---|---|
| contextLength | integer | – | Context window to load with (Ollama num_ctx, LM Studio --context-length) |
| keepAlive | string | – | How long to keep the model resident, e.g. '5m' |
| model | string | yes | Model id/name to load |
| provider | string | – | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| Name | Type | Req | Description |
|---|---|---|---|
| load | object | yes | – |
No examples provided.
model_info Model info ~90
Detailed metadata for one model (family, parameter size, quantization, context length, and layer architecture where available). Without provider, queries the live local providers that have the model.
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | yes | Model id/name to inspect |
| provider | string | – | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| Name | Type | Req | Description |
|---|---|---|---|
| info | object | yes | – |
| model | string | yes | – |
No examples provided.
pull_model Pull model ~129
HEAVY: Download a model onto ONE provider (multiple GB, can take a long time). Streams download progress via MCP progress notifications when the client sends a progressToken. Without provider, uses the provider that already has the model, else the first live local provider that can pull.
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | yes | Model id/name to pull (e.g. qwen3:8b, hf.co/<repo>:<quant>) |
| provider | string | – | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| Name | Type | Req | Description |
|---|---|---|---|
| pull | object | yes | – |
No examples provided.
remove_model Remove model ~121
DESTRUCTIVE: Permanently delete a model from one provider. provider is REQUIRED (no fan-out). If the client supports elicitation the user is asked to confirm directly; otherwise confirm:true is required.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm | boolean | – | Must be true when the client cannot ask the user directly (no elicitation support) |
| model | string | yes | Model id/name to remove |
| provider | string | yes | Provider to delete from (required). Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| Name | Type | Req | Description |
|---|---|---|---|
| remove | object | yes | – |
No examples provided.
search_available Search catalog ~74
Search the built-in curated catalog of well-known local models (Ollama tags) by name, family, or task. Offline and instant. For live results with per-quant fit, use search_models with source 'huggingface'.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | Search text matched against model name, family, and tasks |
| Name | Type | Req | Description |
|---|---|---|---|
| note | string | yes | – |
| query | string | yes | – |
| results | array | yes | – |
No examples provided.
search_models Search models (live) ~189
Find models to download, annotated with whether each fits this machine. source 'huggingface' searches GGUF repos on the Hugging Face Hub and returns per-quant sizes, the best quant for this hardware, and pullable references (Ollama: hf.co/<repo>:<quant>). source 'catalog' searches the offline curated list. The Ollama library has no public search API, so it is not a source.
| Name | Type | Req | Description |
|---|---|---|---|
| contextLength | integer | – | Context length for fit (default 4096) |
| fitsOnly | boolean | – | Only return results with a quant that fits |
| limit | integer | – | Max repos (default 8) |
| query | string | yes | Search text, e.g. 'qwen coder' or 'gemma 3' |
| source | string | – | Default huggingface |
| task | string | – | Catalog source only: filter by task |
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | – |
| results | array | yes | – |
| source | string | yes | – |
No examples provided.
suggest_model Suggest model ~131
Recommend catalog models for a task, ranked for THIS machine: fully-on-GPU first, then partial GPU offload, then CPU-only. Within a tier the largest (most capable) model comes first unless preferSpeed is true. Flags models already installed on a live provider and explains each pick.
| Name | Type | Req | Description |
|---|---|---|---|
| contextLength | integer | – | Context length to plan for (default 4096) |
| kvCacheType | string | – | KV cache precision (default f16) |
| preferSpeed | boolean | – | Prefer smaller, faster models within each tier |
| task | string | yes | The task you want a model for |
| Name | Type | Req | Description |
|---|---|---|---|
| suggestions | array | yes | – |
| task | string | yes | – |
No examples provided.
system_resources System resources ~61
Report local hardware: platform, total/available RAM, CPU count, and GPUs with total/free VRAM (NVIDIA via nvidia-smi, AMD/Intel via sysfs or the Windows registry, Apple Silicon unified memory). Each GPU names its data source.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| cpuCount | number | yes | – |
| gpus | array | yes | – |
| platform | string | yes | – |
| ramFreeBytes | number | yes | – |
| ramTotalBytes | number | yes | – |
No examples provided.
unload_model Unload model ~83
Unload a model from memory to free VRAM/RAM on ONE provider. Without provider, uses the live local provider that has it loaded.
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | yes | Model id/name to unload |
| provider | string | – | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
| Name | Type | Req | Description |
|---|---|---|---|
| unload | object | yes | – |
No examples provided.
How do I install the Local AI MCP server?
Local AI MCP runs locally as an npm package, launched with npx -y @tmhs/local-ai-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @tmhs/local-ai-mcp
claude mcp add tmhsdigital-local-ai-mcp -- npx -y @tmhs/local-ai-mcp
What is the Local AI MCP server?
Local AI MCP is listed in the public MCP registry as io.github.TMHSDigital/local-ai-mcp. Run, fit, and route work to local LLMs (Ollama, LM Studio, llama.cpp, MLX, vLLM, and more). This page covers its npm package (@tmhs/local-ai-mcp).
Is the Local AI MCP server safe to use?
Local AI MCP scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Local AI MCP server expose?
Local AI MCP exposes 19 tools: list_providers, list_models, list_loaded, model_info, pull_model, and 14 more. Their descriptions and schemas cost roughly 2,962 tokens of context every time the server is loaded.
Is the Local AI MCP server still maintained?
Local AI MCP is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Local AI MCP server under?
Local AI MCP declares the CC-BY-NC-ND-4.0 licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.