Cross-venue Polymarket+Kalshi arbitrage: resolution mismatch, void risk & settlement divergence.
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Average 4.5/5 across 2 of 2 tools scored.
The two tools have completely distinct purposes: one lists available events, the other checks risk for a specific pair. No overlap in functionality.
Both tools use consistent verb_noun snake_case naming (list_covered_events, check_resolution_risk), following a clear pattern.
Only 2 tools for a server focused on arbitrage risk analysis. While the pair covers discovery and checking, the scope feels minimal and could benefit from additional tools like execution or monitoring.
The tools cover the core workflow: discover events and check risk for a pair. Minor gaps like not having a tool for individual market details or historical data, but the surface is complete for its pre-trade safety purpose.
check_resolution_riskAPre-trade safety check for cross-venue event markets (crypto oracle-divergence pairs, metered; World Cup football, free). Flags resolution mismatches, void-rule divergence, scope differences (e.g. 90-minute vs extra-time; matched vs differing strike), settlement-source and -timing gaps, stale data, and thin liquidity between the two Polymarket and Kalshi legs BEFORE you execute both. Returns a machine-readable verdict — execution_verdict: safe / caution / block — inside a full Fungibility & Settlement Audit Object (FSAO) with structured findings, top-level divergence flags, venue rule overrides, fee-adjusted spread, and verdict reasons. Identify the pair by EITHER canonical_event_id (a live pair id from list_covered_events — the metered 'crypto:' inventory rolls daily, so fetch a current id there rather than reusing an old one; the free 'wc26:' World Cup pairs are stable) OR market_a + market_b (one Polymarket conditionId + one Kalshi ticker, order-insensitive). If the pair is not covered, returns a non-error coverage reply (covered: false) naming the covered inventories (free World Cup football + metered crypto pairs) and the coverage cutoff instead of an FSAO.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | 'advisory' (default) or 'strict'. | advisory |
| api_key | No | Crosswire API key (cw_…). Optional. Free for the World Cup graph and the first calls/day on metered crypto pairs; beyond that, metered crypto calls draw down this key's prepaid USDC balance (top up via the x402 /v1/credits/topup endpoint). | |
| market_a | No | First leg of the pair to audit (either venue; order does not matter). Provide market_a AND market_b together, or use canonical_event_id instead. | |
| market_b | No | Second leg of the pair to audit (the other venue). | |
| notional_usd | No | Intended position size in USD. Optional; sizes the thin-liquidity check against live top-of-book depth. | |
| canonical_event_id | No | A covered pair id — the outcome-suffixed canonical id. Two namespaces: the metered crypto oracle-divergence inventory (shape 'crypto:btc-above:<date>:strike-<n>#above' — $0.02 USDC per call after 3 free calls/day; the daily pair rolls, so fetch a current id from list_covered_events rather than reusing an old one) and the free World Cup football pairs (shape 'wc26:match:<TEAMS>:<date>:result#home|#draw|#away'; the suffix selects the outcome leg-pair). A bare event id without the suffix is ambiguous and only accepted when market_a + market_b are also given to select the leg. Always get live pair ids from list_covered_events. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes well beyond annotations (readOnlyHint) by detailing the output structure (FSAO with verdict), metering/cost implications, and error handling (coverage reply). It also mentions that the tool returns a 'non-error coverage reply' for uncovered pairs, which is critical behavioral context.
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 long and slightly repetitive (e.g., pair identification stated multiple times). It front-loads the core purpose effectively but includes detailed parameter information that could be more concise. Still, it is well-structured with clear sections for returns, identification, and edge cases.
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 complexity (6 parameters, metering, two identification methods, coverage check), the description covers most relevant aspects: purpose, input methods, output structure, metering, and integration with list_covered_events. It does not detail error conditions beyond coverage, but the output schema likely fills that gap.
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 input schema has 100% coverage, but the description adds significant value beyond schema fields. It explains the two identification methods, provides examples of canonical_event_id namespaces, clarifies optionality and order insensitivity of market parameters, and details api_key usage for metered calls. This helps the agent understand parameter relationships and proper usage.
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's purpose: 'Pre-trade safety check for cross-venue event markets... flags resolution mismatches... BEFORE you execute both.' It identifies the specific resource (cross-venue pairs) and action (check resolution risk), and distinguishes from sibling tool list_covered_events by noting it as a prerequisite for fetching fresh ids.
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 tells when to use the tool ('BEFORE you execute both') and provides two methods for identifying the pair. It directs the agent to list_covered_events for fresh ids when needed, and explains what happens if the pair is not covered. It lacks an explicit 'when not to use' statement but implies its role as a pre-trade check.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_covered_eventsAFree discovery of everything check_resolution_risk can audit across both inventories — the free World Cup football pairs and the metered crypto oracle-divergence pairs (the 'crypto:' namespace is the paid surface: $0.02 USDC per call after 3 free calls/day). Returns the covered canonical events, their per-outcome pair ids (…#home / #draw / #away for football), the Polymarket conditionIds and Kalshi tickers with outcome labels for each pair, match dates, the frozen ruleset_sha pinning the identity graph, the coverage kickoff cutoff, and snapshot freshness. Use a returned pair_id (or a pair's two market ids) as input to check_resolution_risk.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses detailed behavioral information beyond what annotations provide. Annotations only state readOnlyHint=true, but the description explains exactly what is returned (canonical events, per-outcome pair ids, Polymarket conditionIds, Kalshi tickers, match dates, ruleset_sha, coverage kickoff cutoff, snapshot freshness) and mentions pricing for the crypto namespace. No contradiction with annotations.
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 relatively concise given the amount of information conveyed. It front-loads the purpose and covers return values and usage. However, it could be slightly more structured (e.g., bullet points for return fields). Still, every sentence earns its place.
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 has no parameters and an output schema exists (context signal), the description is complete. It explains the return values, usage, pricing, and links to the sibling tool. An agent can correctly invoke this tool without additional guidance.
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 input schema has no parameters (empty object), so there is nothing to add meaning to. With schema description coverage at 100% and zero parameters, the baseline is 4. The description does not need to elaborate on parameters.
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's purpose: 'Free discovery of everything check_resolution_risk can audit across both inventories'. It specifies the resources (World Cup football pairs and crypto oracle-divergence pairs) and the action (discovery). It distinguishes itself from the sibling tool check_resolution_risk by indicating it is the list/discovery counterpart.
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 tells when to use this tool and how its output feeds into the sibling: 'Use a returned pair_id (or a pair's two market ids) as input to check_resolution_risk'. It also provides context about the crypto namespace being paid after 3 free calls. However, it does not explicitly state when not to use it, but the guidance is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!