MacroStress
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FRED_API_KEY | No | API key for FRED, needed to download FRED macro series. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
MacroStress answers one question: how the target indicators of an object are distributed if a given event happens. A scenario s = (N, m, O, D, C) is built from the text of the event and the corpus; the conditions extend the description of the event, and the models compute its consequences.
Read a guide before the work it covers: guide(name="scenario-from-corpus") when the user names an event or asks what happens if it occurs, even without the words scenario or corpus; guide(name="run-report") before a calculation or its report; guide(name="drivers") before work on drivers and satellites; guide(name="model-inputs") before answering the questions of a model that declares inputs; guide(name="elicitation-orchestration") before running that interview with several agents, one per shock. guide() lists them.
When the user asks you to answer a model's questions or to act as its expert, start with elicit(action="next", as_of=..., model_id=...). It gives ONE small question with its schema and answer_call. Copy answer_call, add payload with your own answer object and call elicit again. Each answer saves a part and returns the next question; continue until complete=true. Do not ask the human for numbers, substitute placeholders, or build a full shock table. Partial answers survive restarts but cannot be estimated until all parts pass the full check. elicit(action="list", ...) lists input keys and action="status" says which are complete. Full question/write actions remain under model(kind="inputs"). When complete, model(kind="macro", action="estimate", ...) builds the version from the answers. The questions and the answers live in that tool: reading sources or searching the files of the workspace does not answer them, and several installed models that ask questions need model_id. The agent is the expert of that interview: the numbers are its own quantitative judgements from the state table the question prints and from the model corpus; it does not ask the human for them and does not take them from tests or fixtures. The market variant reads the model corpus, so its answers need that corpus indexed and fetched first.
Search the corpus before writing any number of a scenario. Mark a condition or an impact with "event" when the text of the event states its number, with a corpus fragment only when the fragment gives its number, and with "assumption" otherwise. When neither the event nor the corpus gives a number, propose one from the nearest episode and mark it "assumption": a scenario with no conditions and no impacts records no event, and questions to the user come after the scenario, not instead of it. A human approves a scenario: never fill approved_by yourself and never start a calculation that was not asked for.
A tool that starts a job returns its id at once. Wait with jobs(action="wait", id=): the server holds the call until the job ends, and jobs(action="log", id=) shows what it printed.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| guideA | The working guides of the agent: how to do the work, whatever the client. Without |
| jobsA | Workspace and task state. Actions: state, status, log, cancel, wait.
|
| seriesC | Stored series. Actions: search, get, add, update.
|
| corpusB | The scenario corpus and the model corpus. Actions: search, get, list, add, index, fetch.
|
| scenarioA | Stored scenarios. Actions: list, get, save, validate, reverse. Read |
| runA | Runs on the paths of a scenario. Actions: start, status, result, list. Read |
| portfolioB | Stored portfolios. Actions: list, get, save, delete, check, exposure.
|
| modelA | Model versions and plugins. kind: macro, satellites, inputs, catalog. The episode check of the models is
|
| elicitA | Answer a macro model's questions in small resumable steps. Start with A model that declares inputs is estimated from the agent's own answers, not from the
series: |
| interviewA | Track the interview of a model: ownership, progress, review and corrections.
This tool never writes an answer: the numbers come only through |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| scenario_from_event | Build a scenario from the text of an event, by the corpus, for a human to approve. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
The tools are organized around distinct resources, but there is real overlap between elicit and model(kind="inputs"), and between jobs status/wait and run status. The rich descriptions help, but an agent can still hesitate over which tool owns an operation such as checking a run or supplying model inputs.
Names are consistently lowercase and mostly resource-oriented, which is readable across the set. Minor deviations are 'elicit' as a verb and 'jobs' as a plural among otherwise singular resource nouns.
Ten tools is a reasonable count for a complex macro stress-testing server. However, each tool packs many actions and modes, so the effective surface is much larger than the count suggests, and a few tools such as model and elicit could be cleaner if separated.
The surface covers the core lifecycle: series, portfolios, scenarios, models, elicitation, interviews, runs, and jobs. The main gaps are missing delete operations for several resources such as series, scenarios, and corpus entries, but these are not central blockers for the main workflows.