Skip to main content
Glama
Sign In

Nanotoll MCP

by dev.nanotoll
OverviewDiscussionsAdmin

Server Details

Compress prose for LLM context windows. Per-call USDC billing, signed receipt.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A4.6/5.0

Scored across 2 tools

Disambiguation5/5

check_balance and compress target entirely different operations (account read vs text processing) with no overlap. An agent can trivially tell which to call, and the descriptions reinforce the boundary by explaining when each is needed.

Naming Consistency4/5

Both names are snake_case and readable, but check_balance follows verb_noun while compress is a bare verb, a minor deviation from a single predictable pattern. With only two tools the inconsistency is negligible in practice.

Tool Count3/5

Two tools is on the thin side of the typically well-scoped 3-15 range, though each tool clearly earns its place for a focused compression service. It is borderline but not excessive or mismatched.

Completeness4/5

The surface covers the core lifecycle: compressing text and checking credit/account state, including a receipt for verification. Minor gaps exist (e.g. no standalone receipt verification or usage-history breakdown), but agents can work around them.

Available Tools

2 tools
check_balanceA
Read-onlyIdempotent
Inspect

Read your own account and cost nothing: credit balance left, the USDC funding address to top up, key tier and expiry, and lifetime usage totals. Takes no arguments and is not billed. Call it after an HTTP 402 from compress to see the shortfall, or before a long batch to confirm credit. It reads the account belonging to the API key in your MCP client config (Authorization: Bearer ...) - that is the balance compress bills against.

Inputs: no named parameters.

compressA
Idempotent
Inspect

Compress prose before it enters an LLM context window. Returns the compressed text plus a signed receipt (ratios, refusals, coverage) so the caller can verify what was dropped. Use this instead of truncating or slicing text to fit a budget: truncation drops the tail silently, compression keeps a sentence skeleton and reports what went. Do not use it for source code, config, JSON, diffs or tables - send those verbatim. Very short input (under roughly 2,000 chars) gains little, and verified mode is slower there. To compress a web page, fetch it with the read tool first and compress the markdown it returns, never raw HTML. Prefer deterministic for bulk low-stakes text (free), extractive for ordinary prose, verified when a silently dropped fact would be expensive. Flat per-call price by mode: deterministic free, extractive $0.0008, verified $0.0015 (USDC on Base L2); insufficient credit returns HTTP 402.

Inputs: text (required), squeeze_mode, target_ratio, _idempotency_key.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • Concisr

      EricRdzMtz
      A
      license
      Not graded
      quality
      D
      maintenance
      Token compression for AI contexts, reducing token consumption by compressing conversation exchanges before they enter the LLM context window.
      MIT

    • latent-gate

      KathanModh259
      F
      license
      Not graded
      quality
      B
      maintenance
      Shrinks logs, JSON, docs and web pages before your AI reads them: offline, deterministic, no API key. Folds repetitive log lines (12,037 to 127 tokens on a 400-line log) while code, URLs and quoted strings come back byte-for-byte. Also fetches URLs as clean text, counts tokens exactly, and has optional local Ollama tools for image and text compression.
      72 PyPI
      25
      -

    • token-compressor

      base76-research-lab
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables semantic prompt compression for LLM workflows, reducing token usage by 30-70% while preserving semantic meaning.
      61 PyPI
      12
      MIT
    • genpark-agentic-prompt-compression-token-sieve-skill

      genpark-agentic-promptofficial

      alphaparkinc
      A
      license
      Not graded
      quality
      B
      maintenance
      Compresses multi-turn conversation history by stripping verbose boilerplate and filler tokens while preserving critical tool parameters and named entities, deterministically cutting inference costs by 40-60%. Runs as a zero-dependency Python MCP server or importable module, compatible with Claude Desktop, Cursor, and other MCP runtimes.
      7
      MIT
    Try in Browser
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources