Locallama MCP
未认领An MCP Server that works with Roo Code/Cline.Bot/Claude Desktop to optimize costs by intelligently routing coding tasks between local LLMs free APIs and paid APIs.
工具（18 个）
benchmark_free_models
tasks[], runspertask?, parallel?, maxparalleltasks?
benchmark_model
modelid, providerid?, taskcategories?
benchmark_task
taskid, task, contextlength, expectedoutputlength?, complexity?, localmodel?, paidmodel?, runspertask?
benchmark_tasks
tasks[], runspertask?, parallel?, maxparalleltasks?
cancel_job
jobid
cancel_task
taskid
check_for_updates
—
clear_openrouter_tracking
—
get_cost_estimate
contextlength, expectedoutputlength?, model?
get_free_models
—
get_task_status
taskid
preemptive_route_task
task, contextlength, expectedoutputlength?, complexity?, priority?
reload_config
—
retriv_init
directories[], excludepatterns?, chunksize?, forcereindex?, bm25options?
retriv_search
query, limit?
route_task
task, contextlength, expectedoutputlength?, complexity?, priority?, preemptive?
set_model_prompting_strategy
modelid, systemprompt, userprompt, usechat, assistantprompt?, successrate?, qualityscore?
update_server
—