Skip to content
Agentmart
Submit a tool

Llmxray

What went wrong with your own Ollama calls, in sentences with the fix.

Connector by LogneBudo · GitHub account verified by the MCP Registry

IndexedApache-2.0Local (stdio)★ 28
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/lognebudo-llmxray

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

What went wrong with your own Ollama calls, in sentences with the fix. Local, read-only.

Use cases: model-inference, monitoring-observability

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
22 read · 19 write · 3 delete · 1 not yet classified
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Tools by what they do 45

Read from the source code; the running server may list different tools.

Read 22 · Look things up without changing anything.

  • compare
  • compare_my_turns
  • diagnose_my_turns
  • estimate_my_prompt
  • get_weather
  • help
  • history
  • list_dir
  • list_local_models
  • list_my_turns
  • memories
  • read_file
Show 10 more tools
  • read_llmxray_status
  • read_my_last_turn
  • run_sql
  • search_web
  • session
  • speed
  • status
  • summarize
  • tokens
  • tools

Write 19 · Create, change, send or run things.

  • context
  • copy
  • create_event
  • format
  • mirostat
  • model
  • new
  • rag
  • remember
  • repeat_penalty
  • save
  • seed
Show 7 more tools
  • send_email
  • stop
  • system
  • temperature
  • top_k
  • top_p
  • write_file

Delete 3 · Delete, drop, revoke or wipe things.

  • clear
  • forget
  • reset

Not yet classified 1 · We could not tell from the name and description.

  • new_tool

Secrets and settings it asks for

Other settings (environment variables or headers).

  • LLMXRAY_URL
  • OLLAMA_URL

Network hosts it talks to 8

  • accounts.google.com · found in code
  • docs.google.com · found in code
  • github.com · found in code
  • glama.ai · found in code
  • googleapis.com · found in code
  • host.docker.internal · found in code
  • lognebudo.github.io · found in code
  • oauth2.googleapis.com · found in code

Files it touches

  • Your home directory (~)
  • Any path the agent passes to its tools

Tools (45)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • clear

    Clear current conversation

  • compare

    Navigate to the Compare page

  • compare_my_turnsCompare my turnsread-only

    Did a change help? Medians of cached share, prefill time, generation speed and prompt size for the turns before and after a moment, with the difference and a one-line verdict on the cache. Four tools read your turns, one question each: diagnose_my_turns, is anything wrong (a verdict over several turns); read_my_last_turn, what exactly happened on the latest turn (one turn in full); list_my_turns, what happened turn by turn (the sequence, one line each); compare_my_turns, did a change help (before against after). Use it after you changed a system prompt, keep_alive, num_ctx or the tool list. sp…

  • context

    Set context window size

  • copy

    Copy last assistant response to clipboard

  • create_event

    Create a calendar event.

  • diagnose_my_turnsDiagnose my turnsread-only

    Is anything wrong with the Ollama calls your client sent through LLMxRay on port 11435? A verdict judged over several turns: a prompt rejected or silently cut by the context, the cache lost on every turn or on one turn, a model partly on CPU, tool schemas crowding the prompt. Four tools read your turns, one question each: diagnose_my_turns, is anything wrong (a verdict over several turns); read_my_last_turn, what exactly happened on the latest turn (one turn in full); list_my_turns, what happened turn by turn (the sequence, one line each); compare_my_turns, did a change help (before against af…

  • estimate_my_promptEstimate my promptread-only

    Before sending a prompt of N tokens: whether it fits the context the model is loaded with and the headroom left for the answer. Also whether the model sits in video memory, and how much of the prompt the cache would reuse, from this client's last turn on that model. Use it when a prompt grows, before raising num_ctx, or before switching model. For what is installed use list_local_models; for what actually happened use read_my_last_turn. model: a pulled model name, "gemma4" or "gemma4:latest"; unknown names get the list of pulled ones. prompt_tokens: 1 to 2000000, your estimate of the prompt si…

  • forget

    Forget a previously remembered fact

  • format

    Toggle JSON output format

  • get_weather

    Current weather for a city.

  • help

    Show all available commands

  • history

    Show recent conversations

  • list_dir

    List the files in a folder.

  • list_local_modelsList local modelsread-only

    Which models Ollama has pulled on this machine, with size, parameters and quantisation. Which are loaded now and with what context. How much of each sits in video memory, and whether each pulled model would fit. Use it before choosing a model or a context length. It knows nothing about past calls. For those use diagnose_my_turns or read_my_last_turn. Returns text. A machine line (GPU, video memory, RAM) when LLMxRay is running, then "N models pulled:" and one line per model, sorted by name, ending in LOADED now, fits in VRAM, or larger than VRAM. Takes no arguments, no model name and no filter…

Show 30 more tools
  • list_my_turnsList my turnsread-only

    What happened, turn by turn: the turns your client sent through LLMxRay on port 11435, newest last, one line each: turn number, time, client, model, prompt tokens with cached share, prefill ms, generation speed, stop reason, and flags (reloaded, rejected or cut by the context, error). Four tools read your turns, one question each: diagnose_my_turns, is anything wrong (a verdict over several turns); read_my_last_turn, what exactly happened on the latest turn (one turn in full); list_my_turns, what happened turn by turn (the sequence, one line each); compare_my_turns, did a change help (before a…

  • memories

    Show all remembered facts

  • mirostat

    Set mirostat mode (0=off, 1=v1, 2=v2)

  • model

    Switch model or list available models

  • new

    Start a new chat session

  • new_tool

    A new tool

  • rag

    Toggle RAG context on/off

  • read_file

    Read a text file and return its contents.

  • read_llmxray_statusRead LLMxRay statusread-only

    Where LLMxRay runs and what it holds: the observe port and whether it listens, the Ollama it forwards to and its version, how many turns are kept of the 500 it holds, whether request text is kept on disk, and when it started. Use it first when diagnose_my_turns or read_my_last_turn answers that nothing was seen, or to confirm which Ollama your calls reach. Those tools read the turns; this one reads the server itself. Takes no arguments. Nothing can be changed through MCP; settings live on the Live page. Needs LLMxRay running (npx llmxray); if it is not reachable the answer says so and names th…

  • read_my_last_turnRead my last turnread-only

    What exactly happened on your latest turn through LLMxRay, in numbers: prompt tokens and cached share, prefill time and speed, generated tokens and speed, stop reason, prompt make-up (system, tools, history, new message), context requested, VRAM fit, and where the prompt stopped matching the previous turn. Four tools read your turns, one question each: diagnose_my_turns, is anything wrong (a verdict over several turns); read_my_last_turn, what exactly happened on the latest turn (one turn in full); list_my_turns, what happened turn by turn (the sequence, one line each); compare_my_turns, did a…

  • remember

    Remember a fact about you across conversations

  • repeat_penalty

    Set repeat penalty (1.0-2.0)

  • reset

    Reset all settings to defaults

  • run_sql

    Run a read-only SQL query.

  • save

    Export conversation as JSON or text

  • search_web

    Search the web and return the top results.

  • seed

    Set seed for reproducibility (-1 for random)

  • send_email

    Send an email.

  • session

    View current session details

  • speed

    Show average generation speed across sessions

  • status

    Show Ollama connection status and model info

  • stop

    Set stop sequences (comma-separated)

  • summarize

    Ask the model to summarize the conversation

  • system

    Set the system prompt

  • temperature

    Set temperature (0-2)

  • tokens

    Show token count for current session

  • tools

    Open tools settings panel

  • top_k

    Set top-k sampling (1-100)

  • top_p

    Set top-p / nucleus sampling (0-1)

  • write_file

    Write text to a file, replacing it.

Signals

Stars
28
Forks
3
Open issues
0
Contributors
1
Last commit
Oct 23, 2026 (5 days ago)
Last release
Oct 23, 2026 (5 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.LogneBudo/llmxray
Version
0.8.12
Auth
No auth
Packages
npm llmxray
License
Apache-2.0
Repository
github.com/LogneBudo/llmxray
Website
lognebudo.github.io/llmxray/
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Llmxray MCP server. Agent Mart. https://agentmart.dev/connectors/lognebudo-llmxray (last updated 2026-10-24)