# Sugra API (slim)

> Sugra API, an MCP server by sugra.ai, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Gateway between LLM agents and world data through eight tools and a bundled endpoint catalog.

- Full: https://www.anchorterminal.com/tools/sugra-api-mcp.md (~1,200 tokens) · this version ~1,130 tokens · JSON https://www.anchorterminal.com/tools/sugra-api-mcp.json · canonical https://www.anchorterminal.com/tools/sugra-api-mcp
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05

# Sugra API

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by sugra.ai (https://sugra.ai)
- Category: Model APIs & inference (https://www.anchorterminal.com/categories/inference.md)
- Listed because: It's published in the registry under sugra.ai, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Gateway between LLM agents and world data through eight tools and a bundled endpoint catalog.

## Facts

- MCP registry: `ai.sugra/api-mcp` 0.12.0
- Endpoint: https://app.sugra.ai/mcp (streamable HTTP)
- Package: pypi `sugra-api-mcp` (stdio)
- Source: https://github.com/Sugra-Systems/sugra-api-mcp
- GitHub stars: 3
- Registry entry updated: 2026-09-12

## Tools

- Tools it lists (11, about 6,373 tokens of context, `tools/list` without credentials over MCP 2025-11-25, checked 2026-10-04 22:20 UTC):
  - `sugra_entity_screen` (read-only): Screen a person or organization name against the Sugra sanctions corpus. Returns a SCREENING SIGNAL, not a compliance determination. Sugra is a technology…
  - `sugra_entity_lookup` (read-only): Resolve an entity by identifier and return its composed KYB envelope. `anchor` is `lei` (Legal Entity Identifier, resolved via the GLEIF registry) or `vat` (EU…
  - `search_endpoints` (read-only): Search the bundled Sugra endpoint catalog by natural-language query. Use this to pick an operation_id. It does not fetch data. Typical loop: 1.…
  - `describe_endpoint` (read-only): Describe one Sugra API endpoint by operation_id. Includes agent_hints (duration_class fast/slow/heavy, max_concurrency, bulk billing) so you can budget…
  - `call_endpoint` (read-only): Call a Sugra API endpoint by operation_id from the bundled catalog. Plan calls with describe_endpoint's agent_hints: duration_class "fast" usually responds in…
  - `list_toolsets` (read-only): List catalog groups with endpoint counts and short descriptions. Use the group names as the toolset filter on search_endpoints. This does not call the Sugra…
  - `fetch_data` (read-only): One-step fetch: find the best Sugra endpoint for the query and call it. Combines search_endpoints + call_endpoint into a single round trip. Use this when you…
  - `list_sources` (read-only): List source families in the bundled catalog with endpoint counts. Use the family names as the source filter on search_endpoints. This does not call the Sugra…
  - `resolve_entity` (read-only): Resolve free text to a canonical market or macro entity. Turns a ticker, company name, macro indicator, coin, or currency pair into the agent plane's…
  - `get_snapshot` (read-only): Composed current view of an entity via a named recipe. Executes a fixed server-side recipe (company_snapshot, etf_snapshot, quote_snapshot,…
  - `get_timeseries` (read-only): Bounded timeseries for an entity: price, macro_series, etf_flows or etf_monthly_flows. Returns points oldest-first with an explicit downsampling flag when the…
- How its tools read to an agent (0 errors, 2 warnings, 4 notes, about 6,373 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):
  - warn TC13 get_snapshot: entity.ids (object with no properties)
  - warn TC13 get_timeseries: entity.ids (object with no properties)
  - note TC11 get_snapshot: a parameter is documented in the description but not in the schema: recipe
  - note TC11 get_timeseries: parameters are documented in the description but not in the schema: granularity, max_points, metric
  - note TC11 resolve_entity: parameters are documented in the description but not in the schema: query, type_hint
  - note TC29 server: about 340 tokens (5% of the definitions) are titles that repeat property or function names

- JSON: https://www.anchorterminal.com/api/v1/tools/sugra-api-mcp.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming