token-savior
An MCP server that provides structural codebase indexing and surgical query tools to drastically reduce token usage through symbol-level searches and transitive impact analysis. It supports multiple languages and integrates with git to help AI agents understand code dependencies and the impact of changes in sub-millisecond time.
Limited view. Automated analysis covers part of this stack. Findings reflect what we verified. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
Limited view: static analysis for Python is partially covered.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
Mibayy
Source: Glama · also listed on mcp.so
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
TS_HOOKS_DIRTOKEN_SAVIOR_PROFILE"": "optimized"TS_THIN_SCHEMAS1 off (on in optimized) Strip verbose tool schemas from the manifestTS_AUTO_HOT_K10 Hot-tool count exposed by the telemetry-driven auto profileTS_MEMORY_DISABLEcodebase-memory Persistent code graph With the memory engine =1TS_CAPTURE_DISABLEDTS_PROFILE=tiny_plus =1 python3 bench.py --tasks all --run BTS_CODE_MODE_DISABLE1 off Disable code-mode toolsTOKEN_SAVIOR_BANNERTOKEN_SAVIOR_DEBUG1 off Debug loggingTOKEN_SAVIOR_TRACEoff (bool) MCP request lifecycle tracingTOKEN_SAVIOR_NO_WARMUPoff (bool) Skip the ts_search embedding warm-upTS_RESOURCES_DISABLEDoff (bool) Don't expose observations as ts://obs/{id} MCP resourcesTS_CAPTURE_THRESHOLD_BYTES4096 Minimum tool-output size to sandboxTS_COMPACT_INLINE_THRESHOLD4096 Hybrid mode: compact-result size above which the full original is also sandboxedTS_COMPACT_TINY_THRESHOLD256 Hybrid mode: compact-result size below which the sandbox is always skippedTS_BASH_COMPACTexport =1 # PostToolUse output compactors (34 of them)TS_CAPTURE_REPLACE1 off Strong-replace: tell the agent to ignore the inline output and capture_get the URITS_CAPTURE_TTL_DAYS30 Captures older than this are purged on the next capture_put; 0 disables the GCTOKEN_SAVIOR_STATS_DIR~/.local/share/token-savior Telemetry + stats directoryTOKEN_SAVIOR_CLIENT"": "claude-code",HERMES_GATEWAY_URLHERMES_SESSION_IDCODEX_HOMECODEX_SANDBOXCLAUDECODENot knobs: , CLAUDE_CODE_ENTRYPOINT, CLAUDE_PROJECT_DIR,CLAUDE_CODE_ENTRYPOINTNot knobs: CLAUDECODE, , CLAUDE_PROJECT_DIR,TOKEN_SAVIOR_SESSION_LABELFree-form label attached to session telemetryWORKSPACE_ROOTS"": "/path/to/project1,/path/to/project2",PROJECT_ROOTSingle-root alternative to WORKSPACE_ROOTSTS_WARM_STARToff (bool) Pre-build project slots at startupTOKEN_SAVIOR_AUTODISCOVERTOKEN_SAVIOR_MEMORY_AUTO_SAVE1 off Auto-save memory observationsTOKEN_SAVIOR_CHAIN_NUDGEon 0/false/off disables chained-tool nudgesTS_SEARCH_COLD_DELEGATEoff (bool, on ok) Delegate the cold ts_search call to a running ts daemonTS_STICKY_ACTIVETS_BASH_REWRITE_LOGexport =$HOME/.local/state/token-savior/rewrites.jsonlTS_BASH_REWRITEexport =1 # PreToolUse command rewriter (10 rules)XDG_STATE_HOMETS_DISCIPLINE_GUARDTS_GUARD_OFFCLAUDE_PROJECT_ROOTDeliberate active-project override (Token Savior's own contract — no host sets it). Registered if valid, wins over every other boot signalCLAUDE_PROJECT_DIRNot knobs: CLAUDECODE, CLAUDE_CODE_ENTRYPOINT, ,XDG_CONFIG_HOMEXDG_RUNTIME_DIRTS_SOCK/tmp/ts.sock Unix socket of the ts daemon (CLI + cold delegate)KEYTOKEN_SAVIOR_DASHBOARD_HOST127.0.0.1 Dashboard bind hostTOKEN_SAVIOR_DASHBOARD_PORT8921 Dashboard portTOKEN_SAVIOR_INCLUDE_TMP_PROJECTSoff (bool) Dashboard also lists projects under temp dirsTOKEN_SAVIOR_DATA_DIRXDG_DATA_HOMETOKEN_SAVIOR_VARIABLESTOKEN_SAVIOR_MAX_FILE_SIZE500000 Max file size (bytes) to indexTOKEN_SAVIOR_MAX_FILES10000 Max files per projectTOKEN_SAVIOR_EXCLUDE_PATTERNSColon-separated globs appended at the indexer levelVAREXCLUDE_EXTRAColon-separated globs appended to the default excludesEXCLUDE_PATTERNSbuilt-in list Colon-separated globs; replaces the default exclude listINCLUDE_PATTERNSbuilt-in list Colon-separated globs; replaces the default include listTOKEN_SAVIOR_WATCHERauto File watcher: auto / on / offTS_WATCHER_FORCE_POLLINGoff Force the polling watcher backendTS_CODE_MODE_NODEnode Node binary used by the code-mode sandboxCLAUDE_CONFIG_DIRTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
2/2 tools missing one or more hints — dynamic_tool_228 (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ts_extended (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint). OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tests exist
No test files found
Add tests that exercise each declared tool.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/mibayy/token-savior)?variant=verified to the badge URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check