MCP server for token-budget-aware text truncation. Helps an LLM fit text into a context window mid-task.
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
count_tokensCount the approximate token usage of a text. Optionally compare against a budget and return a 'fits' flag plus overflow. Use as a pre-flight check before assembling a prompt: if count > budget, decide whether to truncate or chunk.Count the approximate token usage of a text. Optionally compare against a budget and return a 'fits' flag plus overflow. Use as a pre-flight check before assembling a prompt: if count > budget, decide whether to truncate or chunk.
No input schema was published for this tool.
truncate_to_token_budgetprivilegedTruncate text to fit within a token budget. Four strategies: head (keep beginning), tail (keep end, good for chat history), head_tail (drop the middle, keep both ends), and smart_cut (head_tail with a visible cut marker). Use when you need to put long text into an LLM context window without going o…Truncate text to fit within a token budget. Four strategies: head (keep beginning), tail (keep end, good for chat history), head_tail (drop the middle, keep both ends), and smart_cut (head_tail with a visible cut marker). Use when you need to put long text into an LLM context window without going o…
No input schema was published for this tool.
chunk_to_budgetSplit a long text into multiple chunks, each at most max_tokens tokens, with optional overlap between adjacent chunks. Use when you have source material too long for one prompt and want to feed it through in pieces (for example, RAG ingestion or a fan-out summarize pattern). Overlap is useful so a…Split a long text into multiple chunks, each at most max_tokens tokens, with optional overlap between adjacent chunks. Use when you have source material too long for one prompt and want to feed it through in pieces (for example, RAG ingestion or a fan-out summarize pattern). Overlap is useful so a…
No input schema was published for this tool.
3 of 3 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
MCP server for token-budget-aware text truncation. Helps an LLM fit text into a context window mid-task.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the depth-4 limit. Anything below that level was never resolved.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
53 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+41 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.