
ReportGem MCP server
Which MCP servers are ReportGem's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-20
- Registry namecom.reportgem/global-researchverified in the MCP registry
The registry name sits under reportgem.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools5
- Server calls itselfReportGem Research MCP
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 11 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- Parameters are untyped or undescribed in 5 of 5 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score83 of 100answers 100 · definitions 83 · context 100 · use 8 · connects 100
- Use1 GitHub stars
- Answered100% of days15 of 15 daily checks
- Median first answer270 ms
- Space in an agent's context≈ 1,339 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results5 of 5 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 5 of 5
What an agent can do with it
- not sure · find equity research reports by broker name
- not sure · browse broker research across technology, financials and healthcare
- not sure · filter research reports by page length
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_research检索研报和论文;返回有界元数据,并在已索引正文命中时返回实际摘录。
search_filings检索美国 SEC 文件和中国公司公告,并返回可核验的内部来源链接。
search_meetings检索全球和中国会议纪要、业绩会记录,区分正文证据与清单命中。
search_visualsSearch indexed charts, tables, industry diagrams and research-relevant images with report/page provenance.
get_evidence返回有界真实摘录或可续读的连续正文窗口;不能把无匹配的资料当作已验证证据。
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"global-research": {
"type": "http",
"url": "https://www.reportgem.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http reportgem https://www.reportgem.com/mcpclaude.ai, ChatGPT and other clients: add https://www.reportgem.com/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.