Schema | token-saver

token-saver

Describes the environment variables required to run the server.

Name	Required	Description	Default
No arguments

Features and capabilities supported by this server

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
check_outputA	Analyze a text output from a Claude API response. Returns an alert level (info/warning/error/alert), token count, whether the output should be suppressed, and detected waste patterns. Use after every API response to catch token-heavy or ignored output early.
get_session_statsA	Return cumulative session statistics: total tokens analyzed, tokens suppressed, and counts of warnings/errors/alerts fired. Use to understand overall waste in the current session.
reset_session_statsA	Reset all session statistics to zero.
analyze_historyA	Analyze a conversation messages array for repetitive or ignored content. Identifies near-duplicate messages and large log-pattern outputs the user likely skipped. Returns suggested truncation count and estimated token savings.
set_modeA	Switch the plugin mode. "off" (default) — plugin is silent, all analysis is skipped. "monitor" — analyze and report but never suppress. "active" — full analysis with suppression. Returns the applied mode.
set_thresholdsB	Override alert thresholds for the current session. All values are in estimated tokens. Returns the applied configuration.

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/flightlesstux/token-saver'

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