Enables retrieval of cross-venue prediction market data from Storm, including Betfair markets, offering tools for listing events, fetching spreads, and managing alerts.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@storm-mcp List the next 20 open politics events on Storm"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server that exposes the Eyewall Markets public prediction-market reference dataset to any Model Context Protocol client.
Eyewall Markets is a market-data and research subscription. It maps the same real-world event across Polymarket, Kalshi, Manifold, ForecastEx, Futuur, Betfair, and other public prediction-market venues into a single canonical record, normalises each venue's published prices for that venue's posted fees, and publishes the comparison. The service is operated autonomously by an AI agent named Storm — there is no human in the loop.
This package is a thin stdio MCP bridge that lets LLM clients — Claude Desktop, Claude Code, Cursor, Zed, and any other MCP-aware host — read Storm's canonical events, recent cross-venue published-price observations, venue reference table, and the subscriber's own notification inbox as native tool calls.
It is intended for analysts, researchers, and agent builders who already have an Eyewall Markets subscription and want their LLM workspace to see what Storm sees. Everything the server returns is descriptive: published-price observations, the event ontology, and notifications a subscriber configured. Nothing returned is a buy or sell recommendation.
The Eyewall Markets API is gated to Edge-tier subscribers ($499/mo). Generate your
api_keyat https://eyewallmarkets.com/account. Lower tiers do not have API access and will receiveHTTP 403from every endpoint this server calls.
API keys are formatted stk_ followed by 48 hex characters (52 characters total) and are scoped to a single account. Treat them like any other bearer credential.
The full API reference lives at https://eyewallmarkets.com/api/docs.
Related MCP server: pmxt-mcp
Edit your Claude Desktop MCP config file and add a storm entry under mcpServers:
{
"mcpServers": {
"storm": {
"command": "npx",
"args": ["-y", "@eyewallmarkets/storm-mcp"],
"env": {
"STORM_API_KEY": "stk_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
}
}
}
}The macOS path is:
~/Library/Application Support/Claude/claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.json· Windows:%APPDATA%\Claude\claude_desktop_config.json.
Restart Claude Desktop. The seven storm_* tools should appear in the tools list inside any new conversation.
claude mcp add storm npx -- -y @eyewallmarkets/storm-mcpThen export the API key into the environment Claude Code spawns the server in (or set it in your shell profile):
export STORM_API_KEY=stk_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxThe exact CLI invocation may vary by Claude Code version; see the official docs at https://docs.claude.com/en/docs/claude-code/mcp for the canonical form (including how to pass env vars on the mcp add line itself).
After install, run /mcp inside Claude Code to confirm the storm server is connected and the seven tools are registered.
Cursor reads MCP server definitions from ~/.cursor/mcp.json. Add the same shape used for Claude Desktop:
{
"mcpServers": {
"storm": {
"command": "npx",
"args": ["-y", "@eyewallmarkets/storm-mcp"],
"env": {
"STORM_API_KEY": "stk_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
}
}
}
}Reload Cursor's MCP integration (Settings → MCP → Refresh).
Zed configures MCP servers under assistant.context_servers in ~/.config/zed/settings.json:
{
"assistant": {
"context_servers": {
"storm": {
"command": "npx",
"args": ["-y", "@eyewallmarkets/storm-mcp"],
"env": {
"STORM_API_KEY": "stk_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
}
}
}
}
}Restart Zed or reload the assistant panel.
All configuration is via environment variables read at server start.
Variable | Required | Default | Description |
| yes | — | Edge-tier api key, format |
| no |
| Override the API root. Useful for staging or a local dev server. |
| no |
| Per-request timeout in milliseconds. |
| no |
| One of |
All seven tools are read-only and idempotent. Argument shapes are documented in JSON-schema-ish form below; the live schema is what the MCP client actually sees.
storm_list_eventsList canonical (cross-venue) events. Cursor-paginated.
{
"limit": { "type": "integer", "default": 50, "max": 200 },
"cursor": { "type": "string", "optional": true },
"category": { "type": "string", "optional": true, "example": "politics" },
"status": { "type": "string", "optional": true, "enum": ["open", "closed", "resolved"] }
}Example prompt: "List the next 20 open politics events on Eyewall Markets."
storm_get_eventFetch a single canonical event by slug, including all linked outcomes and per-venue published prices.
{
"slug": { "type": "string", "required": true, "example": "us-pres-2028" }
}Example prompt: "Pull the full Eyewall Markets record for us-pres-2028 and tell me which outcome has the widest cross-venue published-price difference."
storm_list_spreadsList recent cross-venue published-price observations — events where two venues are publishing different prices for the same canonical outcome. Returns rows whose published-price difference net of venue fees clears the floor, sorted by net_edge_bps DESC.
{
"min_edge_bps": { "type": "integer", "default": 100 },
"limit": { "type": "integer", "default": 50, "max": 200 },
"cursor": { "type": "string", "optional": true }
}Each row reports what each venue is publishing at the observation timestamp; it is descriptive market data, not a buy or sell recommendation, and Eyewall Markets does not warrant fillable depth at any price returned.
Example prompt: "Show me the top 10 cross-venue published-price observations on Eyewall Markets where net_edge_bps >= 250."
storm_get_marketLook up a single venue/market record by (venue_slug, external_id).
{
"venue": { "type": "string", "required": true, "example": "polymarket" },
"external_id": { "type": "string", "required": true }
}Example prompt: "Look up Polymarket market 0xabc... on Eyewall Markets."
storm_list_venuesList every venue Eyewall Markets covers, with regulatory posture (CFTC-registered DCM, offshore, etc.), posted fee schedules, and capability flags (orderbook, AMM, parimutuel). Reference data only — venue eligibility for any individual user is governed by the venue and the user's local law.
{}Example prompt: "Which of the venues Eyewall Markets covers are CFTC-registered DCMs?"
storm_get_alerts_inboxPoll the subscriber's api-channel notification inbox. Edge subscribers can route notifications to the api delivery channel; this tool drains the unack'd queue.
{
"since": { "type": "integer", "minimum": 0, "optional": true, "example": 4521 }
}The cursor is the integer id of the last notification you've seen. Pass next_since from the previous response to fetch only newer items; omit to read from the subscriber's persisted ack cursor. Each item is a descriptive notification — it names the canonical event, the two venues, the prices each venue was publishing at the observation timestamp, and the notification rule that matched.
Example prompt: "Poll my Eyewall Markets inbox and summarise everything I haven't acked."
storm_ack_alertsAdvance the persistent ack cursor so future inbox polls skip already-handled items. The cursor is server-side and survives across MCP sessions.
{
"up_to": { "type": "integer", "minimum": 0, "required": true, "example": 4530 }
}Example prompt: "Ack all Eyewall Markets notifications up to right now."
User: Find me 2028-election cross-venue observations on Eyewall Markets where
net_edge_bps >= 300and tell me which three events have the widest published-price differences.Assistant: (calls
storm_list_spreadswithmin_edge_bps: 300, limit: 50, filters the response by event slug prefix2028_us_presidential_, then callsstorm_get_eventon the top three to enrich)Returns the three 2028-election events with the widest currently-published cross-venue price differences, the venue pair on each side, and which venue is publishing the lower price. Descriptive market data only; not a recommendation.
User: Poll my Eyewall Markets inbox and summarise unack'd notifications, then ack everything you summarised.
Assistant: (calls
storm_get_alerts_inboxwith nosince, summarises the items by category, then callsstorm_ack_alertswithup_toset to the largestidit saw)Returns a categorised summary of unack'd notifications (cross-venue published-price observations that matched a rule, venue-status changes, resolution events) and confirms the cursor advance so subsequent polls only return new items.
The Eyewall Markets API enforces 10 requests per second per api key server-side. If you exceed that, the server returns HTTP 429 with Retry-After: 1. This MCP bridge does not retry automatically; it surfaces the error to the LLM as plain text content in the tool result so the model can decide whether to back off, retry, or give up.
Errors are returned to the LLM in this shape (text content on the tool result, isError: true):
Storm API error (HTTP 429, rate_limited): too many requests Retry after 1000 ms.Storm API error (HTTP 403, edge_tier_required): edge_tier_requiredStorm API error (HTTP 401, invalid_credentials): invalid_credentialsNetwork-level failures (DNS, TCP, TLS, timeout) surface as:
Storm API error (HTTP 0, transport): request timeoutThe full HTTP status, server error code, and human message are always included so the LLM can act on them.
git clone https://github.com/xch1tbllc/storm-mcp.git
cd storm-mcp
npm install
npm testPoint at a local Storm dev server by overriding the API base:
STORM_API_BASE=http://localhost:8080/api/v1 \
STORM_API_KEY=stk_dev_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx \
node src/index.mjsThe server speaks stdio MCP, so you can drive it directly with any MCP test harness or by piping JSON-RPC frames in by hand.
Tests use Node's built-in test runner; no Jest, no Vitest, no transpiler.
MIT — see LICENSE.
© 2026 XCH1TB, LLC dba Eyewall Markets.
Storm itself — the autonomous AI agent that operates Eyewall Markets and produces the data this server exposes — is a separate, internal codebase. This package is only the client-facing MCP bridge to Eyewall Markets' public read-only API surface.
This software and the data it surfaces are provided for informational purposes only. Eyewall Markets is a market-data and research subscription, not a broker, exchange, trading platform, or financial advisor. The service does not place orders on any venue, does not custody funds, and does not recommend buying or selling any contract. Nothing returned by this MCP server is legal, financial, tax, or investment advice.
Prediction-market participation is subject to your local laws and to each venue's own eligibility rules; in particular, Polymarket is restricted in the United States under CFTC orders and is not available to most US persons. Venue eligibility is the user's responsibility — not Eyewall Markets', not Storm's, and not this server's. Eyewall Markets aggregates publicly observable market state and does not place trades on anyone's behalf.
Eyewall Markets is operated autonomously by an AI agent named Storm. Storm polls each covered venue's public read endpoint, normalises the observations, decides which observations match a subscriber's notification rule, dispatches notifications, and answers support mail at storm@eyewallmarkets.com. There is no human in the loop — no reviewer queue, no support team behind the inbox, no analyst checking matches before they go live. Errors are made and corrected by software. The methodology page describes the provenance Storm stamps onto every match so a reader can see what was decided by a deterministic rule, what by an LLM proposal, and what by Storm's autonomous review.
Advance the persistent ack cursor to the given sequence id, removing items at or below it from the api-channel inbox. Call this after the LLM / agent has processed items returned by storm_get_alerts_inbox; otherwise the same items will keep being returned. Sourced from Eyewall Markets / Storm. The cursor is server-side and survives across MCP sessions.
| Name | Required | Description | Default |
|---|---|---|---|
| up_to | Yes | Ack all alerts with sequence id <= up_to. Use the highest id seen in storm_get_alerts_inbox. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that the cursor is persistent, server-side, survives sessions, and that items are removed. This is sufficient for a mutation tool of this complexity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences cover action, usage, and persistence. Every sentence adds necessary information with no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple acknowledgment tool with one parameter and no output schema, the description covers behavior, usage context, and parameter guidance. Minor gap: does not mention any potential side effects, but overall complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and schema already describes the parameter. The description adds value by advising to use the highest id seen in storm_get_alerts_inbox, which is practical guidance beyond the raw schema definition.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('advance the persistent ack cursor' and 'removing items') and the resource ('api-channel inbox'). It distinguishes itself from the sibling tool storm_get_alerts_inbox by focusing on acknowledgment and removal.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly instructs to call this after processing items from storm_get_alerts_inbox to avoid duplicates. It provides clear context on when to use, though it does not elaborate on when not to use or list alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Poll the subscriber's api-channel notification inbox for cross-venue price-difference and event notifications that haven't been ack'd yet. Each item is a descriptive notification — it names the canonical event, the two venues, the prices each venue was publishing at the observation timestamp, and the rule that matched. Sourced from Eyewall Markets / Storm. Pass the next_since returned by the previous call as since to get only newer items. After processing, call storm_ack_alerts to advance the persistent cursor.
| Name | Required | Description | Default |
|---|---|---|---|
| since | No | Only return alerts with sequence id strictly greater than this. Defaults to 0 (full inbox). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of explaining behavior. It states that the tool returns unacknowledged notifications, explains cursor-based pagination, and implies a read-only operation. It does not mention rate limits or other details, but the core behavioral traits are well covered.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at three sentences, each serving a distinct purpose: purpose explanation, content description, and usage pattern with next steps. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no output schema, no annotations) and the complexity of the polling pattern, the description is fully complete. It explains the tool, pagination, and the required follow-up action, leaving no critical gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'since' is fully described in the schema (100% coverage), and the description adds significant value by explaining its role in pagination and instructing how to use the 'next_since' value from previous calls. This goes beyond the schema's basic constraint.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the tool's purpose: to poll the subscriber's api-channel notification inbox for unacknowledged cross-venue price-difference and event notifications. It names the verb 'poll', the resource 'inbox', and details the content of each notification, distinguishing it from the related 'storm_ack_alerts' tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on pagination (using 'next_since' from previous call as 'since') and directs users to call 'storm_ack_alerts' after processing to advance the cursor. While it doesn't explicitly state when not to use the tool, the context is clear and the alternative is named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch a single canonical event by its Storm slug, including the full set of cross-venue markets attached to that event and each venue's currently published price. Use after storm_list_events when you need the canonical question text, resolution criteria, and per-venue market handles. Sourced from Eyewall Markets / Storm; describes the published-price observation, not a buy or sell recommendation.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Storm event slug, e.g. 'will-fed-cut-rates-by-2026-q3'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but description implies read-only fetch and adds context that data is observational, not advisory. However, it does not disclose any side effects, auth needs, or limitations beyond that.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two succinct sentences: first defines action and scope, second provides usage guidance and disclaimer. No redundant text; all information is relevant and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple input and lack of output schema, the description covers core purpose, usage context, and key outputs (question text, resolution criteria, market handles). Missing exact response structure but acceptable for this complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a well-described parameter. The description does not add significant meaning beyond the schema, so a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool fetches a single canonical event by slug, including markets and prices. It distinguishes from sibling 'storm_list_events' by specifying it's for detailed event data after listing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly suggests using after storm_list_events and states the need for canonical question text, resolution criteria, and market handles. Includes disclaimer that it's observation, not a recommendation, but does not explicitly mention alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch the canonical Storm view of a single market on a specific venue, including the venue's currently published bid/ask, volume, and the canonical event it's joined to. Use when you have a venue + the venue's native market id (e.g. a Kalshi ticker or Polymarket condition id) and want Storm's normalized representation. Sourced from Eyewall Markets / Storm; describes published price snapshots from the venue's public read endpoints, not a recommendation.
| Name | Required | Description | Default |
|---|---|---|---|
| venue | Yes | Venue slug, e.g. 'kalshi' or 'polymarket'. See storm_list_venues. | |
| external_id | Yes | The venue's native market identifier (Kalshi ticker, Polymarket condition id, etc.). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but description states it fetches from public read endpoints and is not a recommendation, indicating a safe read operation. Could mention if real-time or cached, but still good.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with purpose, no unnecessary words. Efficiently conveys all essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, description adequately covers return fields (bid/ask, volume, canonical event) and notes it's not a recommendation. Sufficient for simple two-parameter tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with clear explanations for venue and external_id. The description reinforces the usage but doesn't add significant new constraints or examples beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool fetches the canonical Storm view of a single market, including bid/ask, volume, and associated event. It distinguishes itself from sibling tools like storm_list_events and storm_get_event.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use when you have a venue + the venue's native market id', providing clear conditions. Also references storm_list_venues for obtaining the slug, guiding the agent on prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List canonical prediction-market events (questions/topics) tracked by Eyewall Markets / Storm across the public venues it covers (Kalshi, Polymarket, Manifold, ForecastEx, and others). Use this to discover what events exist before drilling into a specific event with storm_get_event. Supports filtering by category (e.g. 'politics', 'economics') and status (e.g. 'open', 'resolved'), and is cursor-paginated. Read-only market reference data; describes the event ontology, not a recommendation.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Page size (1-100). Default server-side is typically 25. | |
| cursor | No | Opaque pagination cursor returned in next_cursor from a previous call. | |
| category | No | Filter to a single category slug, e.g. 'politics'. | |
| status | No | Filter by event status, e.g. 'open' or 'resolved'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but description declares 'Read-only market reference data' and mentions cursor-pagination. Lacks details on rate limits or auth, but sufficient for basic safety.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, front-loaded with purpose, each sentence adds value (use case, filtering, pagination, read-only nature). No fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, but description mentions cursor-paginated results. Could specify return fields, but adequate for discovering events before drilling down.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. Description adds examples for category and status, but no deeper semantics beyond schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool lists prediction-market events with specific venues (Kalshi, Polymarket, etc.), uses the verb 'list' and resource 'events', and distinguishes from sibling tool storm_get_event.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this to discover what events exist before drilling into a specific event with storm_get_event', providing a clear use case and alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List recent cross-venue published-price observations — pairs of markets on different venues that are publishing different prices for the same canonical outcome. Returns rows whose published-price difference net of each venue's posted fees clears the configured floor, ordered by net_edge_bps DESC. Sourced from Eyewall Markets / Storm. Descriptive market-data only: each row reports what each venue is publishing, not a buy or sell recommendation, and does not warrant fillable depth at any price reported.
| Name | Required | Description | Default |
|---|---|---|---|
| min_edge_bps | No | Minimum published-price difference net of venue fees, in basis points (1 bp = 0.01%). E.g. 50 returns only rows whose net_edge_bps is >= 50. Defaults to the server-side floor. | |
| limit | No | Page size (1-100). | |
| cursor | No | Opaque pagination cursor returned in next_cursor from a previous call. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses behavioral traits: lists recent observations, filters by configured floor, orders by net_edge_bps descending, and emphasizes that data is descriptive and non-actionable. This covers safety and operational expectations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise—two sentences that front-load the primary purpose in the first sentence and add behavioral caveats in the second. No extraneous words or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (3 parameters, no output schema), the description covers key aspects: what is returned, ordering, and behavioral constraints. However, it does not mention pagination handling (cursor/next_cursor) explicitly, leaving that to the schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds value by explaining min_edge_bps with an example and mentioning server-side floor default. However, for 'limit' and 'cursor', no additional semantic context is provided beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and the resource 'cross-venue published-price observations', and distinguishes this tool from siblings like storm_list_events and storm_list_venues by specifying its unique function of identifying pricing disparities between venues.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states the tool's purpose and clarifies that it provides descriptive market data only, not buy/sell recommendations or depth warranties. However, it does not explicitly mention when not to use this tool or provide direct alternatives beyond sibling differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all public prediction-market venues covered by Eyewall Markets / Storm, with their slugs, display names, regulatory posture (CFTC-registered DCM, offshore, etc.), posted fee schedules, capability flags (orderbook / AMM / parimutuel), and current ingestion status. Call this first when you need the venue slug to pass to storm_get_market. Reference data only — venue eligibility for any individual user is governed by the venue and the user's local law.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the tool is reference data only and lists the kind of data returned, which is sufficient for a read-only tool with no side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the action and output, every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description thoroughly enumerates return fields (slugs, display names, regulatory posture, etc.) and clarifies it's reference data, making it complete for agent use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so baseline is 4. The description adds meaning by explaining what the output contains, compensating for the empty schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('List all public prediction-market venues') and specifies the output fields, distinguishing it from siblings like storm_get_market which needs a slug.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs 'Call this first when you need the venue slug to pass to storm_get_market', providing clear when-to-use guidance and noting that eligibility is governed by venue and local law.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.2storm_ack_alertsstorm_get_alerts_inboxstorm_get_eventstorm_get_marketstorm_list_eventsstorm_list_spreadsstorm_list_venuesScored across 7 tools
Each tool targets a distinct action or resource: acking alerts, polling inbox, fetching events/markets, listing events/spreads/venues. No two tools have overlapping purposes, and descriptions clearly differentiate them.
All tools follow a consistent 'storm_verb_noun' pattern in snake_case, with verbs like ack, get, list. This makes it easy for an agent to infer functionality from names.
7 tools is a well-scoped set for a prediction market data server. Each tool serves a necessary function without unnecessary duplication or gaps, covering discovery, detailed queries, and notification management.
The tool set covers the full lifecycle: discovering events (list), drilling into details (get), accessing markets (get), monitoring spreads and alerts, acknowledging alerts, and listing venues. No obvious missing operations for the stated purpose.
Hosted MCP for Kalshi prediction markets: search, odds, order books, settlement rules, and trading.
Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP server exposing the Backtest360 engine API as tools for AI agents.
MCP server for OpenMM — exposes market data, account, trading, and strategy tools to AI agents
