ai-economics-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AI_ECONOMICS_API | No | Point at a self-hosted instance | https://piszczek.pl/tools/api |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| revocation_exposureA | Revocation Exposure: How long does a revoked token keep working across gateways, caches and workers? Returns the worst-case exposure window, an A–F grade and the weakest enforcement point. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/revocation-exposure. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence. |
| proof_adjusted_autonomyA | Proof-Adjusted Autonomy (PAA): How autonomous is an AI agent once proof is required? PAA = P(A) × P(C|A) × P(R|A,C) × P(T|A,C,R). Returns the honest percentage, the gap vs claimed autonomy and the single gate where +5pp pays most. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/proof-adjusted-autonomy. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence. |
| token_costA | AI Token Cost: What does a monthly token volume cost across GPT, Claude, Gemini and DeepSeek? Input/output priced separately, prompt-cache discount applied. Returns the ranked bill per model. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/token-cost. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence. |
| context_windowA | Context Window: How many tokens is this content, does it fit the window, and what does carrying it cost per request? All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/context-window. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence. |
| agent_hourA | Agent-Hour Cost: Fully-loaded cost of one AI agent-hour: compute plus human verification, vs the human hour it replaces. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/agent-hour. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence. |
| model_routingA | Model Routing Savings: How much does routing the routable share of a workload to a cheaper tier save per month and per year? All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/model-routing. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence. |
| llm_energyA | LLM Energy: How much electricity does an AI query use? Tokens → Wh, joules, dollars, CO₂ and real-world equivalents. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/llm-energy. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence. |
| joules_per_verified_taskA | Joules per Verified Task: Which model is most energy-efficient per task that actually passes verification? E = tokens × J/token ÷ pass rate — a lighter model with a lower pass rate can still win. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/joules-per-verified-task. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence. |
| token_burnA | Token Burn Meter: Org-wide token burn as money, kilowatt-hours, CO₂ and households powered — per day and per year. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/token-burn. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence. |
| humanoid_energyA | Humanoid Energy Budget: How long can a humanoid robot run per charge? Splits the battery between actuation, inference and idle. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/humanoid-energy. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence. |
| verification_bottleneckA | Verification Bottleneck: Agents generate in parallel, humans review in series. Computes the real agent-fleet ceiling from review capacity, minutes per task and rework rate. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/verification-bottleneck. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence. |
| proof_debtA | Proof Debt Accumulator: What does unverified AI work cost over time? Backlog, deferred-review premium and expected incident liability. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/proof-debt. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Each tool targets a distinct metric, so an agent can generally tell them apart. However, several tools cluster around cost/energy/verification themes, and token_burn, token_cost, and llm_energy could be confused at a glance without reading the descriptions closely.
All tool names follow the same lowercase snake_case convention and are descriptive noun phrases representing metrics. Even though they are not verb_noun names, the pattern is consistent and predictable across the entire set.
Twelve tools is well within the ideal range for a specialized calculator server. Each tool earns its place by covering a distinct AI economics or energy metric, and the count is neither thin nor bloated.
The suite covers token costs, energy use, verification, autonomy, routing, and agent-hour economics, which forms a coherent calculator surface. Minor adjacent gaps exist, such as training-cost modeling or scenario comparison, but agents can usually combine existing outputs to work around them.