mrmarket.ai is a remote MCP server that resolves financial research questions against clean, structured market data. Multi-factor screens, rankings, cohort-relative comparisons, point-in-time event studies, and forward-return analysis across 11,000+ US-listed tickers, returned as structured rows.
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 9 tools
Each tool has a clearly distinct purpose: describe_data for catalog, query_data for main analysis, fetch_page for pagination, get_symbols for lookups, getting_started for onboarding, get_account_status for account info, recent_queries for history, list_tickets for ticket listing, and report_issue for support. No two tools overlap significantly.
Most tools follow a consistent verb_noun pattern (e.g., describe_data, fetch_page, query_data). Minor deviations: 'getting_started' uses a gerund instead of imperative verb, and 'recent_queries' is adjective_noun rather than verb_noun. Overall pattern is easily recognizable.
With 9 tools, the server is well-scoped. It covers the essential functions for a financial data query service without being overwhelming. Each tool serves a clear role, and the count feels appropriate for the domain.
The tool set covers the full lifecycle: data discovery (describe_data), query (query_data), pagination (fetch_page), symbol lookup (get_symbols), account management (get_account_status), onboarding (getting_started), issue reporting (report_issue), history (recent_queries), and ticket tracking (list_tickets). No obvious gaps for the advertised purpose.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
list_tickets2 fields changedInput schema / properties / limit / exclusiveMinimumRemoved value: -0Input schema / properties / limit / minimumAdded value: +1recent_queries2 fields changedInput schema / properties / limit / exclusiveMinimumRemoved value: -0Input schema / properties / limit / minimumAdded value: +1query_data1 field changedInput schema / properties / visualizeAdded value: +{
+ "description": "Opt-in charting for the shareable view_url. Default false returns a plain table link (cheapest). Set true when the user wants a chart or stat card: the link is then rendered with the chart type the engine picks from the data shape — a single-row result becomes a \"stat\" card, a multi-period series a line chart, etc. Does not change the JSON rows you receive, only how the view_url renders.",
+ "type": "boolean"
+}list_ticketsquery_data5 fields changedInput schema / properties / clarification_modeAdded value: +{
+ "description": "\"auto\" (default): ambiguous questions are resolved via elicitation or sensible server defaults in one call. \"return\": the server returns status \"clarification_needed\" with the questions + recommended defaults and does NOT proceed (and does not charge); answer by re-calling query_data with `clarifications`. Use \"return\" when silent defaults are not acceptable for your user.",
+ "enum": [
+ "auto",
+ "return"
+ ],
+ "type": "string"
+}Input schema / properties / clarificationsAdded value: +{
+ "description": "Answers to a prior clarification_needed response (pass each question verbatim with your chosen answer). Use together with clarification_mode: \"return\" for a two-step round-trip.",
+ "items": {
+ "properties": {
+ "answer": {
+ "type": "string"
+ },
+ "question": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "question",
+ "answer"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+}Input schema / properties / question / descriptionPrevious value: -"Full natural-language financial question. Not SQL. For complex multi-step workflows (backtests, Monte Carlo, multi-factor scoring), decompose into multiple calls — see mrmarket://capabilities resource."New value: +"ONE natural-language financial question, max 100 words (hard limit — longer is rejected as QUESTION_TOO_LONG, free of charge). Not SQL. Be precise, not redundant: metric(s) + universe/filters + time range is enough; the server picks columns and thresholds. Put ticker lists in `symbols`, never in this text. If 100 words feels tight, you are bundling multiple questions — split them into separate calls (see mrmarket://capabilities for the split test)."Input schema / properties / question / maxLengthAdded value: +4000Input schema / properties / symbolsAdded value: +{
+ "description": "Explicit ticker universe for this question (e.g., a screening batch). STRONGLY preferred over pasting long ticker lists into `question`: the list is applied mechanically as a symbol filter (exact, order-independent), keeps the question readable, and is cheaper. Phrase the question generically (\"Find every golden cross event…\") and put the tickers here.",
+ "items": {
+ "type": "string"
+ },
+ "maxItems": 2000,
+ "type": "array"
+}describe_datafetch_pageget_account_statusget_symbolsgetting_startedquery_datarecent_queriesreport_issue
Add one secure layer between your agents and this server.