FitLLM
REMOTE · FITLLM.RUN · SCANNED SEP 20
Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability87
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 823 tokens (~117/item across 7 items; 3 tools + 4 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 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
How do I install the FitLLM MCP server?
FitLLM is a hosted endpoint at https://fitllm.run/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · fitllm.run
claude mcp add --transport http run-fitllm-fitllm 'https://fitllm.run/api/mcp'
{
"mcpServers": {
"run-fitllm-fitllm": {
"url": "https://fitllm.run/api/mcp"
}
}
} {
"servers": {
"run-fitllm-fitllm": {
"type": "http",
"url": "https://fitllm.run/api/mcp"
}
}
} [mcp_servers.run-fitllm-fitllm] url = "https://fitllm.run/api/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"run-fitllm-fitllm": {
"type": "remote",
"url": "https://fitllm.run/api/mcp",
"enabled": true
}
}
} openclaw mcp add run-fitllm-fitllm --url 'https://fitllm.run/api/mcp' --transport streamable-http
mcp_servers:
run-fitllm-fitllm:
url: "https://fitllm.run/api/mcp" {
"McpServers": {
"run-fitllm-fitllm": {
"Transport": "http",
"Url": "https://fitllm.run/api/mcp"
}
}
} assistant mcp add run-fitllm-fitllm -t streamable-http -u 'https://fitllm.run/api/mcp'
{
"mcpServers": {
"run-fitllm-fitllm": {
"type": "http",
"url": "https://fitllm.run/api/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
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 Sept 26 0
- Schema quality: pass → fail ▼ functional
- “check_llm_fit” added an optional parameter “ctx” cosmetic
- “check_llm_fit” reworded the description of “context_tokens” cosmetic
- 3 Sept 26 +7
- Authorization: unverified → partial ▲ security
- Tool “check_llm_fit” rewrote its description, which is the text the model reads security
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Aug 26 +1
- Stability: 0.97 → pass security
- 24 Aug 26 0
- Tool “list_supported” rewrote its description, which is the text the model reads security
- 23 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 31 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
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 20 Sept 2026 · Probed https://fitllm.run/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=fitllm.run | CN=YR1,O=Let's Encrypt,C=US | 25 Jul 2026 | 23 Oct 2026 | RSA 2048 | SHA256-RSA | 5a4973b56999d6aa287adbce47dd431550e |
| SANs: fitllm.run | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of fitllm.run. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| run. | present | 37315 | 8 | Verified |
| fitllm.run. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://fitllm.run/api/mcp | Verified | 200 | |
| http (plaintext) | http://fitllm.run/api/mcp | HTTPS enforced | 308 | https://fitllm.run/api/mcp |
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 →
check_llm_fit Check if an LLM fits on hardware ~455
Check whether a specific local LLM fits in the memory of a specific GPU or Apple Silicon Mac. Returns fits/tight/won't-fit verdict with the memory breakdown (weights, KV cache, linear-attention state when present, runtime overhead, reserve), max context, and a concrete fix if it doesn't fit. Use this whenever a user asks anything like "can I run <model> on my <GPU/Mac>?", "will <model> fit in <N>GB?", or "what do I need to run <model>?". Estimates using curated, config-derived architecture fields (MLA, sliding-window, hybrid attention, MoE modeled).
| Name | Type | Req | Description |
|---|---|---|---|
| context_tokens | integer | – | Context length in tokens (default 8192). Alias: ctx (same field as the REST API). |
| ctx | integer | – | Alias of context_tokens — accepted because the REST API uses this name. Do not pass both with different values. |
| gpu | string | – | GPU name, fuzzy — e.g. "RTX 4090", "RX 7900 XTX", "A100 80GB". Multi-GPU rigs: join with + — e.g. "RTX 5090 + RTX 3090" (VRAM pools across cards). Provide gpu OR mac_ram_gb. |
| gpu_count | integer | – | Number of identical copies of the gpu (e.g. gpu="RTX 3090", gpu_count=2 for a 2×3090 rig). Default 1. |
| kv_bits | number | – | KV-cache quantization bits (default 16 = F16) |
| mac_ram_gb | integer | – | Apple Silicon unified memory in GB — e.g. 16, 64, 512. Provide gpu OR mac_ram_gb. |
| model | string | yes | LLM name, fuzzy — e.g. "GLM-4.7-Flash", "gpt-oss-20b", "gemma 31b" |
| quant | string | – | Weight quantization. GPU: Q4_K_M(default)/Q5_K_M/Q6_K/Q8_0/FP16. Mac: 4/8(default)/16 (bits). |
No output schema declared.
No examples provided.
list_supported List supported models & hardware ~54
List the built-in model names and hardware names this fit-checker knows (for mapping user wording to exact names). Standard text-only HuggingFace transformer configs can also be checked via fitllm.run; unsupported architectures are rejected.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
what_fits_on_hardware What LLMs fit on this hardware ~176
Rank which popular local LLMs fit on a given GPU or Apple Silicon Mac (at ~4-bit quantization, 8K context) — models that fit come first, biggest first, with max context each. Use when a user asks "what can I run on my <GPU/Mac/N GB>?", "best local model for my machine?", or gives hardware without naming a model.
| Name | Type | Req | Description |
|---|---|---|---|
| gpu | string | – | GPU name, fuzzy. Multi-GPU rigs: join with + (e.g. "RTX 5090 + RTX 3090"). Provide gpu OR mac_ram_gb. |
| gpu_count | integer | – | Number of identical copies of the gpu. Default 1. |
| mac_ram_gb | integer | – | Apple Silicon unified memory GB. Provide gpu OR mac_ram_gb. |
No output schema declared.
No examples provided.
What is the FitLLM MCP server?
FitLLM is an MCP server listed in the public MCP registry as run.fitllm/fitllm. Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only. This page covers its hosted endpoint (https://fitllm.run/api/mcp).
Is the FitLLM MCP server safe to use?
FitLLM scores 90 out of 100 on VerifyMCP. 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 FitLLM MCP server expose?
FitLLM exposes 3 tools: check_llm_fit, what_fits_on_hardware, list_supported. Their descriptions and schemas cost roughly 685 tokens of context every time the server is loaded.
Does the FitLLM MCP server require authentication?
No. We connected to FitLLM without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the FitLLM MCP server still maintained?
FitLLM is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.