tokencast
Lets you estimate LLM costs before running agent workflows, then learns from actual usage to improve accuracy over time. Exposes five MCP tools: estimate_cost takes size, file count, and complexity to predict token spend across research, architecture, and code steps with optimistic/expected/pessimistic bands. After work completes, report_session feeds actual costs back into a calibration system that adjusts future estimates. Ships with a Claude Code plugin that auto-triggers estimation after planning agents and records session data at shutdown. Also works standalone in Cursor, VS Code, and Windsurf. Useful when you're running multi-step agentic workflows and want to avoid surprise API bills or need budget guardrails before kicking off expensive tasks.
- GitHub stars
- 1
- tools
- 5
- transport
- STDIO
- last updated
- Mar 28, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
estimate_costEstimate API cost for a planned task before running it
Estimate API cost for a planned task before running it
No parameter schema in public metadata yet.
get_calibration_statusCheck whether your estimates are well-calibrated
Check whether your estimates are well-calibrated
No parameter schema in public metadata yet.
get_cost_historyBrowse past estimates vs actuals
Browse past estimates vs actuals
No parameter schema in public metadata yet.
report_sessionReport actual cost at session end to improve calibration
Report actual cost at session end to improve calibration
No parameter schema in public metadata yet.
report_step_costRecord the cost of a single pipeline step during a session
Record the cost of a single pipeline step during a session
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
tokencast logo
tokencast
Pre-execution cost estimation for LLM agent workflows. Get a cost estimate before running any agent task, then let tokencast learn from actuals to improve accuracy over time.
Available as a Claude Code plugin (recommended — one command delivers everything) or as an MCP server for Cursor, VS Code + Copilot, and Windsurf.
Installation
Claude Code (Recommended)
Install tokencast as a Claude Code plugin — delivers the MCP server, calibration hooks, and estimation skill in two commands:
/plugin marketplace add krulewis/tokencast
/plugin install tokencast@tokencast
The first command registers the tokencast marketplace. The second installs the plugin from it.
Details
- Repository
- github.com/krulewis/tokencast
- Category
- AI & LLM Tools
- Package
tokencast- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Task Graph Mcpoortonaut/task-graph-mcpMCP server for agent task workflows with phases, prompts, gates, and multi-agent coordination1stars
Hivemindquantulabs/hivemindQuery multiple AI models (OpenAI, Anthropic, Google) for consensus responses.1stars
Sutra4rgon4ut/sutraContext Engineering Engine. Provides cognitive tools, memory structures, and agent patterns.0stars
Krtrai.krtr/krtrPre-diligence AI for founders, investors, and firms — multi-agent pitch analysis and deal flow.0stars
Observe Instrument Mcpalanzha2/observe-instrument-mcpAdd OpenTelemetry tracing to Python AI agents. Supports LangGraph, LlamaIndex, CrewAI, OpenAI SDK.0stars
API Lockerapilocker/apilockerEncrypted credential vault: LLM, service & OAuth keys. 21-tool MCP server for your AI agent.0stars