@ooples/token-optimizer-mcp
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 1 of 1 tool tried
Contacts while installing and starting: nothing
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y -p @ooples/token-optimizer-mcp@7.11.0 token-optimizer-mcp
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
1 tool that takes no input and looks read-only was called once with nothing. 1 returned a result.
get_optimization_report | Returned a result 0.1 s · 5,351 characters |
During the calls it contacted nothing it had not already contacted.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
wiki_write claim, anchors, evidence, applicability, type, confidence, confidenceLabel, scope, invalidators, sessionId, trigger, projectRoot
Record a durable finding in this project's knowledge graph so a later session retrieves it instead of re-deriving it. Use it the moment you conclude something that cost real work and is not obvious from the code: a dead end and why, a decision and its rejected alternatives, a command that finally worked, or how a subsystem fits together. Anchor it to the files it is about — the anchor is what lets the claim be invalidated when that code changes, and what makes it surface automatically when the file is next touched. Costs nothing and sends nothing off the machine.
wiki_query operation, key, query, type, nodeId, limit, graphDir, projectRoot, sessionId
Read the project's knowledge graph: fetch a finding by key, search findings by terms, inspect a node and its neighbours, or get the graph's audit, token balance and overall shape. Use it when the session index mentions a finding you want in full, or to find out what the graph holds at all. NOT for anchored retrieval: to ask what is known about a particular file or symbol, call wiki_read, which does exactly that and is the tool the enforcement layer points at.
expand ref, section, reason, claim, anchor
Retrieve the full output behind a preview reference, served from the local store rather than by re-running anything. Pass `section` to say which named part of the preview you needed -- that is what teaches the next preview to keep it. Pass `claim` and `anchor` to record what you learned, so the same expansion never happens again.
optimize_session sessionId, min_token_threshold
Analyzes operations in the current session from the session JSONL log, identifies large text blocks from file-based tools (Read, Write, Edit), compresses them, and stores them in the cache to reduce future token usage. Returns a summary of the optimization.
smart_read path, diffMode, maxSize, chunkSize, chunkIndex, enableCache, ttl, preserveStructure, includeMetadata, encoding
Read files with intelligent caching, diff-based updates, and syntax-aware optimization. Measured token reduction vs reading the file: -2% to 0% first read, 99-99.9% repeated on an unchanged file (bench/tools, 3 fixtures) -- a first read returns the file plus a one-field header, so it still costs a little more than reading the file; the saving is on the repeat.
5 more tools
smart_write path, content, verifyBeforeWrite, atomic, autoFormat, returnDiff, createBackup, tempDir, formatType, trackChanges, updateCache, ttl, createDirectories, encoding, mode
Write files with an unmeasured design target of 85% token reduction through verification, atomic operations, and change tracking
smart_edit path, operations, dryRun, returnDiff, createBackup, verifyBeforeApply, batchEdits, contextLines, updateCache, ttl, encoding
Edit files with an unmeasured design target of 90% token reduction through line-based operations and diff-only output
smart_glob pattern, path, cwd, includeMetadata, includeContent, extensions, limit, sortBy, absolute, deadlineMs, ignore, onlyFiles, onlyDirectories, excludeExtensions, minSize, maxSize, modifiedAfter, modifiedBefore, maxContentSize, offset, sortOrder, useCache, ttl
Search files with glob patterns and an unmeasured design target of 75% token reduction through path-only results and smart filtering
smart_grep pattern, path, cwd, files, caseSensitive, regex, extensions, includeContext, contextBefore, contextAfter, limit, filesWithMatches, count, wholeWord, excludeExtensions, skipBinary, deadlineMs, ignore, includeIgnored, includeColumn, maxMatchesPerFile, offset, useCache, ttl, maxFileSize, encoding
Search file contents with an unmeasured design target of 80% token reduction through match-only output and smart filtering
get_optimization_report startDate, endDate, sessionId, topN
Get a provenance-gated token report. Verified savings require a materialized MCP payload before and after optimization; historical and tool-reported estimates are excluded. Direct API-price equivalents use each exact captured model and route; ambiguous operations remain unpriced.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Files it wrote
/tmp/ .token-optimizer/ unrooted/ .token-optimizer/ wiki/ metrics.jsonl /tmp/ .token-optimizer/ unrooted/ .token-optimizer/ wiki/ evidence.jsonl /tmp/ .token-optimizer/ unrooted/ .token-optimizer/ wiki/ .gitignore /tmp/ .token-optimizer/ projects/ 734b6779e8ce3384/ store/ wiki/ artifacts/ a40124e98c73118c.txt /tmp/ .token-optimizer/ projects/ 734b6779e8ce3384/ store/ wiki/ artifacts/ f484538614ff0c27.txt /tmp/ .token-optimizer/ projects/ 734b6779e8ce3384/ store/ wiki/ metrics.jsonl /tmp/ .token-optimizer/ projects/ 734b6779e8ce3384/ store/ wiki/ .gitignore /tmp/ .token-optimizer/ projects/ 734b6779e8ce3384/ meta.json /tmp/ .token-optimizer/ config.json /tmp/ .token-optimizer/ optimization.db-wal /tmp/ .token-optimizer/ optimization.db /tmp/ .token-optimizer/ logs/ mcp-events-2026-11-16-96-0.jsonl /tmp/ .token-optimizer/ optimization.db-shm /tmp/ .token-optimizer-cache/ cache.db-wal /tmp/ .token-optimizer-cache/ cache.db-shm /tmp/ .token-optimizer-cache/ cache.db /tmp/ .token-optimizer-mcp/ analytics.db
Paths inside its sandbox, where its home folder is /tmp and its own folder cannot be written to.
Install facts
| License | MIT |
|---|---|
| Needs | node ^22.18.0 || >=24.11.0 |
| Source | github.com/ooples/token-optimizer-mcp |
| Install scripts | @ooples/token-optimizer-mcp declare them. This runner does not run them. |
| Tarball | sha512-slww1v2V0osy/4GIM8uV9Ei4Hob/p7x/aB/1ChtPhxH8hg+CX8w78KPtLEWK89hYFUF+D4gEhnunKd0kY9q5aA== |
Versions reported
| Version | Run | Result | Tools |
|---|---|---|---|
| 7.11.0 | 2026-11-16 | Starts with no setup | 10 |
| 7.10.0 | 2026-11-12 | Starts with no setup | 10 |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/%40ooples/token-optimizer-mcp)
New version out? Ask for a fresh report.