Check normalized portfolios against mandates and calculate allocation constraints.
Scored across 10 tools
Most tools target distinct resources/actions, and the three analytical tools (constraints, statistics, alignment) are differentiated by their descriptions (arithmetic checks vs. historical metrics vs. mandate comparison). The three list_* tools are also separable by resource, though the calculate/evaluate cluster could still be momentarily confused.
All 10 tools follow a consistent snake_case verb_noun pattern (calculate_*, cancel_*, evaluate_*, get_*, list_*, review_*, upload_*). The convention is predictable throughout with no mixed styles.
10 tools is well-scoped for a portfolio analytics workflow, covering ingestion, profiling, calculation, and retrieval without bloat. Each tool appears to earn its place.
The surface covers the full lifecycle: upload, cancel/stage, profile review, list series/portfolios, and three analysis tools plus get/list analyses. Minor gaps like no delete/rerun-analysis operation exist but core workflows are covered.
Calculate explicit portfolio constraints deterministically from normalized holdings. Use this for arithmetic checks, not for interpreting natural-language mandates.
Inputs: holdings (required), constraints (required), idempotency_key (required), analysis_name, +3 more. Returns: object
Calculate historical return, volatility, drawdown, risk-adjusted and benchmark-relative statistics from a confirmed portfolio series profile. The metrics parameter describes all available calculations and their required inputs. Use daily, weekly or monthly complete periods; results include coverage, warnings and exact dataset/profile pins. Reuse an idempotency_key only for an identical calculation.
Inputs: metrics (required), idempotency_key (required), target_frequency (required), series_profile_id (required), +6 more. Returns: object
Cancel a pending upload and permanently remove its staging chunks.
Inputs: upload_id (required), analysis_name. Returns: status, upload_id, analysis_id, analysis_url, +3 more
Compare a clean mandate with normalized holdings. Do not send PDF, CSV, spreadsheet, or factsheet files; extract them before calling.
Inputs: holdings (required), idempotency_key (required), rules, mandate, +5 more. Returns: object
Read retained normalized inputs, operations, results and owner-scoped dataset references. This is not an external agent transcript.
Inputs: analysis_id (required). Returns: url, kinds, steps, title, +10 more
Read private calculation groups and independent operations. Filter by kind, portfolio, dates, ready/running/attention status or legacy open/finished status.
Inputs: kind, page, status, date_to, +3 more. Returns: page, total, analyses, has_more, +1 more
List owner-scoped portfolios, analytics datasets, and profile readiness.
Inputs: no named parameters. Returns: portfolios
Discover owner-scoped immutable series profiles and their exact dataset versions. This returns metadata and coverage only, never dataset rows.
Inputs: cursor, statuses, page_size, portfolio_id. Returns: series, next_cursor
Create an immutable profile revision using revise, or explicitly confirm a warning-free proposal with confirmation=true.
Inputs: action (required), profile_id (required), revisions, confirmation, +1 more. Returns: analysis_id, analysis_url, analysis_name, series_profile
Upload normalized series_key/date/value/distribution rows and commit a dataset version. For up to 5,000 rows, omit chunk_index and total_chunks to complete in one call. For larger inputs, declare total_chunks on every call, send chunks in order, and reuse upload_id and idempotency_key. The final chunk automatically verifies and commits all data and returns immutable series profiles. Parse files locally before calling.
Inputs: rows (required), idempotency_key (required), source, upload_id, +9 more. Returns: status, row_count, upload_id, dataset_id, +21 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Size an entire sports betting slate as one portfolio, using fractional Kelly and exposure limits.
Deterministic decision guardrail for AI agents and bots. Verifies pre-trade economics (long-only).
Policy check on a described yield position. Complement to yieldhunter. Research only.
Interface requirements, missing-decision checks, and public frontend portfolio information.
Add one secure layer between your agents and this server.