Skip to main content
Glama
magna-nz

Tallybook

by magna-nz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Go
Local

Related Servers

Alternatives to Tallybook

No user-submitted related servers found.

    Related Servers

    • token-meter

      whdrnr2583-cmd
      A
      license
      A
      quality
      A
      maintenance
      Local-first dashboard + MCP server that parses Claude Code and Codex JSONL files into a SQLite cost / token tracker. Per-MCP and per-tool breakdown, session drill-down, dedup by request_id; never talks to vendor APIs
      5
      100
      1
      MIT

    • ai-usage-mcp

      MohitBansal321
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables local-first tracking of AI token usage and costs from Claude Code and OpenCode, answering queries about tokens, models, sessions, and cost through MCP tools and a CLI, with no network calls.
      161
      1
      MIT

    • agent-eval

      mrd5591
      A
      license
      A
      quality
      B
      maintenance
      Enables analyzing coding-agent session transcripts to measure tool efficiency, detect loops, track test outcomes, and report costs, with MCP tools for listing sessions, analyzing sessions, finding loops, and generating cost reports.
      4
      MIT

    • contextburn

      arsentev-ai
      A
      license
      B
      quality
      A
      maintenance
      Lets a coding agent inspect its own run efficiency mid-session from local Claude Code transcripts, exposing the share of paid tokens that became model output versus context re-reading. Ships two stdio tools — one returning the shares as structured data and one returning the full cost-weighted report — with no network calls.
      2
      MIT
    Deploy Server
    RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

    TDQS

    A3.8/5.0

    Scored across 8 tools

    Disambiguation4/5

    Most tools target distinct facets: report (aggregate), sessions (list), session (single), agents (sub-agent breakdown), changes (model-change points), finding (one finding), prices, refresh. The main risk is report vs sessions vs agents overlapping in cost-summary territory, and session vs sessions differing only by plural, but descriptions clearly separate them.

    Naming Consistency4/5

    All names are single lowercase nouns (agents, changes, finding, prices, refresh, report, session, sessions), so the convention is applied consistently. The only weakness is session/sessions and agents/sessions reading similarly, which slightly hurts predictability.

    Tool Count5/5

    Eight tools is well-scoped for a cost-tracking server, with each tool mapping to a clear function (scan, price table, aggregate report, listing, drill-down, sub-agent detail, model-change tracking, findings). Nothing appears redundant or padded.

    Completeness5/5

    The surface covers the full lifecycle: refresh to ingest data, prices for computation basis, report/sessions/agents for aggregate and sub-agent views, session for turn-level drill-down, changes for model change comparisons, and finding for full advice with evidence. No obvious gaps or dead ends for the stated purpose.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources