tinkoff-wealth-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| investor_sync_dataC | Synchronize broker and market data. Read-only in MVP. |
| investor_get_sync_statusA | Return last sync status and data freshness. |
| investor_get_profileB | Return investment goals, risk profile, and limits. |
| investor_save_profileB | Save local investment profile. Does not change broker data. |
| investor_list_accountsC | List broker accounts available for analysis. |
| investor_select_accountsC | Select broker accounts included in portfolio analysis. |
| investor_get_portfolioB | Return current aggregated portfolio. |
| investor_analyze_portfolioC | Analyze allocation, concentration, and goal deviation. |
| investor_explain_portfolio_changeB | Explain portfolio change for a period. Date range uses from_date/to_date. |
| investor_get_operationsC | Return account operations for a date range (from_date/to_date). |
| investor_get_instrumentC | Return instrument card and portfolio position. |
| investor_scan_risksC | Scan portfolio risk signals. |
| investor_get_news_digestB | Dynamic research brief: portfolio-derived targets + tailored search queries. The server does NOT fetch news; it computes WHAT to look up (top issuers/sectors, rate sensitivity) from the current holdings. The assistant then web-searches the returned research_targets and reports the impact on the portfolio. |
| investor_recommend_next_actionC | Recommend next analytical action, usually for a cash contribution. |
| investor_simulate_actionA | Simulate buy/sell/reduce/increase actions as a 'what-if'. Each action is {action, instrument: {id_type, id}, amount: {amount, currency}}. Does NOT place any broker order. |
| investor_generate_reportC | Generate a portfolio report (markdown or json). |
| investor_get_goal_progressC | Progress to the user's long-term goals: capital target %, passive-income coverage (coupons + dividends vs target), and a rough timeline projection. |
| investor_get_bond_calendarC | Bond calendar: upcoming coupons/maturities/offers, maturity ladder, 12m coupon income. |
| investor_research_instrumentC | Prepare an instrument/issuer research draft (external sources not wired yet).
|
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| portfolio_weekly_review | |
| portfolio_drop_explainer | |
| next_purchase_advice | |
| instrument_deep_dive | |
| risk_review |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| profile_resource | Current investment profile. |
| accounts_resource | Broker accounts selected for analysis. |
| portfolio_resource | Current aggregated portfolio. |
| risks_resource | Current portfolio risk signals. |
| domain_schema_resource | Description of the normalized domain model. |
TDQS
Scored across 19 tools
Each tool targets a specific distinct function (e.g., get_portfolio vs analyze_portfolio, get_instrument vs research_instrument). Even closely related tools like get_portfolio and analyze_portfolio have clearly different purposes, so an agent can reliably select the correct tool.
All tools use the consistent prefix 'investor_' followed by a verb_noun pattern in snake_case (e.g., get_portfolio, simulate_action, scan_risks). There is no mixing of styles or vague verbs, making the naming predictable and easy to learn.
With 19 tools, the count is on the higher side but still appropriate for a comprehensive wealth management analysis server. Each tool appears justified for covering portfolio analysis, research, sync, and simulation without being bloated.
The tool set covers the full analytical lifecycle: data retrieval (get_portfolio, get_operations), analysis (analyze_portfolio, scan_risks), simulation (simulate_action), reporting (generate_report), research (research_instrument), and configuration (select_accounts, save_profile). There are no obvious gaps for a read-only analysis tool.