Lium Docs
REMOTE · DOCS.LIUM.IO
Search and read the Lium GPU rental docs: pods, CLI, SDK, REST API and agent guides.
Available components
Last scanned (1 day ago)
Scores higher than 0% of remote servers
Unreachable. Last reached 21 Oct 2026.
Category Cloud Infrastructure
Deleted
This server was marked deleted in the MCP registry on 2026-10-21 16:33:38.141669+00.
Its details are retained for reference, and this page is not indexed.
The registry records this reason: Replaced by io.github.Datura-ai/lium-gpu-cloud.
Recent critical change
Authorization (21 Oct 2026). See the changelog before you install this server.
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 Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (remove_pod). See how to fix → View diagnostics → Fail
- 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 Usability71
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1486 tokens (~135/item across 11 items; 11 tools + 0 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 Management70
- Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 12 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.
- 22 Oct 26 −75
The score moved with no change recorded against any check. We would rather say so than guess.
- 21 Oct 26 −8
- Authorization: partial → fail ▼ critical
- The server rewrote its instructions, which are the text every model session reads security
- New tool “remove_pod”, which the server declares destructive security
- Tool “list_templates” rewrote its description, which is the text the model reads security
- Tool “get_gpu_prices” rewrote its description, which is the text the model reads security
- Tool “search” rewrote its description, which is the text the model reads security
- Tool “search_gpus” rewrote its description, which is the text the model reads security
- Schema quality: pass → fail ▼ functional
- Schema quality: excellent → good functional
- Destructive annotations: pass → 100 functional
- New tool “estimate_provider_earnings” functional
- New tool “get_balance” functional
- New tool “get_pod” functional
- New tool “list_pods” functional
- New tool “list_templates” functional
- New tool “rent_pod” functional
- “get_gpu_prices” added an optional parameter “count” cosmetic
- “rent_pod” reworded the description of “wait_seconds” cosmetic
- 20 Oct 26 0
- Schema quality: 89 → 103 ▼ functional
- New tool “get_gpu_prices” functional
- New tool “search_gpus” functional
- 19 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Oct 26 +7
- Authorization: unverified → partial ▲ security
- Tool “read_page” changed its title: Read a Lium docs page cosmetic
- Tool “search” changed its title: Search Lium docs cosmetic
- 16 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 37. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
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 22 Oct 2026 · Probed https://docs.lium.io/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=lium.io | CN=Amazon RSA 2048 M04,O=Amazon,C=US | 22 Dec 2025 | 20 Jan 2027 | RSA 2048 | SHA256-RSA | 4e7fa7ce800053d0aca0ebbc84a799d |
| SANs: lium.io, *.prod.lium.io, *.staging.lium.io, *.lium.io, *.dev.lium.io | ||||||
| CN=Amazon RSA 2048 M04,O=Amazon,C=US (CA) | CN=Amazon Root CA 1,O=Amazon,C=US | 23 Aug 2022 | 23 Aug 2030 | RSA 2048 | SHA256-RSA | 773124f2a952e3ed18a58bdb85d1bc0ce5f27 |
| CN=Amazon Root CA 1,O=Amazon,C=US (CA) | CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US | 25 May 2015 | 31 Dec 2037 | RSA 2048 | SHA256-RSA | 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6 |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of docs.lium.io. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| io. | present | 57355 | 8 | Verified |
| lium.io. | 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=31536000 |
| content-security-policy | frame-ancestors 'none' |
| x-frame-options | DENY |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://docs.lium.io/mcp | Verified | 200 | |
| http (plaintext) | http://docs.lium.io/mcp | HTTPS enforced | 301 | https://docs.lium.io/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 →
estimate_provider_earnings Estimate Lium provider earnings ~157
Estimate what a provider earns per month on Lium by listing GPUs of a model, as the rewards calculator does: rental income (95% of the renter price) and rented extra at the last 30 days' utilisation, plus idle pay at the validator's rate for every unrented hour; with what those GPUs actually earned and the middle-half range across providers. Use when someone asks what their GPUs could earn on Lium; for renting GPUs use search_gpus. An estimate, not a guarantee.
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | How many GPUs of that model (default 1) |
| gpu | string | yes | GPU model, e.g. H100, B200, RTX 4090 (case and spacing ignored) |
No output schema declared.
No examples provided.
get_balance My Lium balance ~15
Your Lium balance in USD.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_gpu_prices Lium GPU prices ~157
Live price range (min, median, max USD per GPU-hour) and free GPU count for each GPU model rentable on Lium right now. Use for "what does an H100 cost" or comparing models; use search_gpus to pick a node to rent. Pass count for multi-GPU quotes: a 1-GPU price can come from a node with one free GPU.
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | GPUs needed on one node: prices only nodes that can rent that many |
| country | string | – | Two-letter country code, e.g. US, DE |
| gpu | string | – | GPU model, e.g. H100, H200, B200, RTX 4090 (case and spacing ignored) |
No output schema declared.
No examples provided.
get_pod Get a Lium pod ~47
One pod: status, ssh command (once RUNNING), price per hour and spend so far.
| Name | Type | Req | Description |
|---|---|---|---|
| pod_id | string | yes | Pod id from rent_pod or list_pods |
No output schema declared.
No examples provided.
list_pods List my Lium pods ~23
Your Lium pods with status, ssh command and price per hour.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_templates List Lium templates ~63
Docker templates a pod can start from (official ones, your own and other users' public ones; official and yours mark which), for rent_pod template_id.
| Name | Type | Req | Description |
|---|---|---|---|
| search | string | – | Filter by name or image, e.g. pytorch, vllm |
No output schema declared.
No examples provided.
read_page Read a Lium docs page ~102
Return the raw Markdown source for a documentation page. Accepts a full URL, absolute slug (e.g. /providers/quickstart), or basename (e.g. quickstart). On tie among basenames, prefers pages in audience order: Providers > Validators > Renters > Developers.
| Name | Type | Req | Description |
|---|---|---|---|
| url_or_slug | string | yes | Full URL (https://docs.lium.io/providers/quickstart), absolute slug (/providers/quickstart), or basename (quickstart) |
No output schema declared.
No examples provided.
remove_pod Remove a Lium pod ~56
Request pod deletion. Billing stops when accepted; deletion may finish asynchronously (get_pod shows DELETING). Data on the pod is lost.
| Name | Type | Req | Description |
|---|---|---|---|
| pod_id | string | yes | Pod id from rent_pod or list_pods |
No output schema declared.
No examples provided.
rent_pod Rent a Lium GPU pod ~381
Rent a GPU pod on Lium with your API key and wait until it runs; returns the pod id and the ssh command. Spends money from your Lium balance: the pod is billed per second until remove_pod, also when idle. Give gpu (and count, optional max_price_per_gpu_hour and country) to let Lium pick the cheapest matching node, or node_id from search_gpus alone for that node. idempotency_key is required: if a call fails or times out, retry with the same key within 24 hours so it cannot rent twice.
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | GPUs on one node (default: 1 with gpu, every free GPU with node_id) |
| country | string | – | Two-letter country code (with gpu, not node_id) |
| gpu | string | – | GPU model, e.g. H100, RTX 4090; Lium picks the cheapest node that fits |
| idempotency_key | string | yes | A new unique string per rental (e.g. a UUID). Send the same key again within 24 hours to retry the same rental: it never rents twice |
| max_price_per_gpu_hour | number | – | Price cap in USD per GPU-hour (with gpu, not node_id) |
| name | string | – | Pod name |
| node_id | string | – | A node id from search_gpus, to rent that node |
| ssh_public_key | string | – | OpenSSH public key to log in with (e.g. ~/.ssh/id_ed25519.pub); default: the keys saved on your Lium account |
| template_id | string | – | From list_templates; default: Lium's PyTorch image for the node |
| wait_seconds | integer | – | How long to wait for the pod to run (default 25, max 50) |
No output schema declared.
No examples provided.
search Search Lium docs ~131
Search the Lium documentation for pages matching the query. Use for how-to questions (renting, SSH, templates, providing GPUs); for live GPU availability or prices use search_gpus or get_gpu_prices instead. Optionally filter by audience (providers, validators, pod-users, developers); without one, pages for the other side (renter or provider, guessed from the query) rank lower.
| Name | Type | Req | Description |
|---|---|---|---|
| audience | string | – | Filter results to a specific audience section |
| limit | integer | – | Maximum number of results to return (default 10, max 50) |
| query | string | yes | Search query |
No output schema declared.
No examples provided.
search_gpus Find rentable Lium GPUs ~201
List GPU nodes that can be rented on Lium right now, cheapest per GPU-hour first, with live USD prices and a rent link for each. Use when the user wants a specific machine (GPU model, count, country, price cap); use get_gpu_prices for a price overview. Each node has tier (secure or spot), reliability_score and min_gpus_per_rental (some nodes rent only whole). Read-only: next_step says how to rent one.
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | GPUs needed on one node |
| country | string | – | Two-letter country code, e.g. US, DE |
| gpu | string | – | GPU model, e.g. H100, H200, B200, RTX 4090 (case and spacing ignored) |
| limit | integer | – | Max nodes to return (default 10, max 50) |
| max_price_per_gpu_hour | number | – | Price cap in USD per GPU-hour |
No output schema declared.
No examples provided.
What is the Lium Docs MCP server?
Lium Docs is an MCP server listed in the public MCP registry as io.github.Datura-ai/lium-docs. Search and read the Lium GPU rental docs: pods, CLI, SDK, REST API and agent guides. This page covers its hosted endpoint (https://docs.lium.io/mcp).
Is the Lium Docs MCP server safe to use?
Lium Docs scores 0 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 Lium Docs MCP server expose?
Lium Docs exposes 11 tools: search, read_page, search_gpus, get_gpu_prices, estimate_provider_earnings, and 6 more. Their descriptions and schemas cost roughly 1,333 tokens of context every time the server is loaded.
Does the Lium Docs MCP server require authentication?
No. We connected to Lium Docs without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Lium Docs MCP server still maintained?
Lium Docs has been deleted from the MCP registry. We last reached this channel on 21 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.