Skip to main content
Glama
This connector has been deprecated

Replaced by echopai-mcp.

Duplicate listing; superseded by io.github.echopai/echopai-mcp (official MCP Registry entry).

views

KEY FIELDS (per item): report.title (nullable, only compact/full; index uses title), source_label (the institution; no institution), ai_summary, content (+ content_truncated), primary_security.canonical_code / .name / .recommend_action, full_text_available, published_at, id (for report). PRIMARY research source for stock judgement: analyst views and sell-side reports with research_entity_id attribution — prefer over news. Only ~10% of items have full_text_available=true, so an all-false page says nothing; pass report_only=true for the report stream, then report each. Default fields=compact (summary + ~300 chars); fields=index (~150 B/row) for a first pass over many rows, full only when needed. A+H: pass the A-share canonical for consolidated coverage.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "views"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoHistory range end (inclusive, China date; defaults to today). Use with from.
_jqNoJMESPath,对 data 求值(写 items[*].id)
codeNoFilter by security canonical_code (e.g. SSE:600519, HK:00700, US:AAPL)
fromNoHistory range start (China date YYYY-MM-DD). Range mode: needs a filter; Pro-only up to 365 days back.
limitNoMax items per page
_spillNotrue=全量落盘,只回摘要与取数地址
fieldsNoResponse shape: `index` (thinnest, ~150 B/row: id, published_at, source_label, primary security canonical_code/security_name/recommend_action, one-line headline, full_text_available, doc_kind — no body; 60 rows ≈ 9 KB, list-then-pick), `compact` (default — ai_summary + first ~300 chars; `securities` lists only non-primary names, `attachment` only kind/name) or `full` (complete content).
offsetNoPagination offset for paging through long history ranges.
_fieldsNo逗号分隔的直接字段;有 items 时投影每行,否则投影 data;外层字段或嵌套结构用 _jq
_intentNo用户原问题一句话,仅分析用,可留空
analystNoAnalyst Chinese name (exact / fuzzy)
_max_bytesNo响应字节上限,默认约 50 KB
since_daysNoLookback in days. ≤30 = rolling feed; >30 switches to range history (needs code / analyst / institution; Pro up to 365). `limit` applies newest-first within the window — read `actual_window` and page with `offset` if it falls short.
institutionNoBroker / institution Chinese name
report_onlyNotrue = only formal research reports, i.e. views whose full text is archived and readable via `report` (full_text_available). Omit for the mixed feed (~10% reports). Use true whenever the task is to actually read sell-side research.
_max_bytes_modeNo正文超限处理,默认 truncate 保留前缀

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full burden, and it discloses several non-obvious traits: only ~10% of items have `full_text_available=true` (so an all-false page is not evidence of absence), `limit` applies newest-first within the window requiring `offset` paging when `actual_window` falls short, range mode requires a filter and is Pro-only to 365 days, and the byte/size costs of each `fields` mode. Gaps remain around permissions/quotas beyond the 'Pro-only' note, but the sampling and pagination caveats are the important ones and are covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every sentence carries information, but the ordering is poor for scanning: it front-loads a dense 'KEY FIELDS' inventory with parenthetical negations ('no `institution`', 'index uses `title`') before establishing what the tool is. The telegraphic, all-caps, arrow-laden style compresses well for a repeat user but slows first-time tool selection.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 16-parameter tool with no annotations and no output schema, the description covers the essentials well: it documents the returned fields (necessary since no output schema exists), the three response shapes, pagination and window behavior, and defaults. What it omits is the nature of the four control parameters (`_jq`, `_fields`, `_spill`, `_max_bytes_mode`), which are only explained by the schema, plus any statement of auth/tier constraints beyond the Pro mention.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so a baseline of 3 applies; the description earns a notch above because it gives decision-level meaning the schema lacks — the concrete tradeoff between `index`/`compact`/`full` with row-size estimates, the 10% `full_text_available` rate that motivates `report_only`, and the A+H canonical-consolidation rule. Some of it (the `since_days` window-switch text) simply restates the schema's own parameter description rather than adding to it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource specifically — 'analyst views and sell-side reports with research_entity_id attribution' — and differentiates it from `news` ('prefer over') and from `report` (the follow-up read tool). However, it never opens with a verb+resource statement (e.g. 'List analyst views...'); the first line launches into per-item field documentation, so the purpose must be assembled from the middle of a dense paragraph.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use and when-not-to-use guidance is present: this is the 'PRIMARY research source for stock judgement... prefer over `news`', and the correct two-step flow is spelled out ('pass `report_only=true` for the report stream, then `report` each'). It also gives selection rules among the tool's own modes — `index` for a first pass over many rows, `compact` default, `full` only when needed — and the A+H canonical rule for consolidated coverage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources