Schema | agy-ollama-mcp

agy-ollama-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`OLLAMA_HOST`	No	Endpoint of the local Ollama daemon.	http://localhost:11434
`OLLAMA_NUM_CTX`	No	Context window size allocated in local model memory.	16384
`OLLAMA_TIMEOUT`	No	Request timeout in seconds for generation tasks.	180
`LOCAL_LLM_MODEL`	No	Preferred model override (e.g. qwen2.5-coder:14b, deepseek-r1:14b). Auto-detected if not set.
`OLLAMA_MCP_DEBUG`	No	Set to '1' to enable verbose diagnostic output to stderr.	0
`OLLAMA_TEMPERATURE`	No	Sampling temperature for code generation.	0.2

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
local_draft_codeA	Generate initial code drafts, boilerplate, unit tests, or scaffolding locally via Ollama without consuming cloud tokens.
local_summarize_and_extractC	Compress massive files, logs, terminal traces, or documentation into high-density summaries before cloud reasoning.
local_chunked_summaryC	Map-reduce chunked summarization for massive files or logs that exceed single context limits.
local_extract_jsonB	Extract structured JSON from unstructured text, logs, or documentation according to a target schema description.
local_list_modelsA	List all models currently installed and available in the local Ollama instance.
local_prewarm_modelA	Pre-warm a local model into memory/VRAM with keep_alive=-1 so subsequent calls have zero cold-start delay.
local_map_reduce_fileB	Compress large files, traces, or logs using local Ollama Map-Reduce before ingesting into context.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/leifdavisson/agy-ollama-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server