Skip to content
FinChiefs logo

FinChiefs MCP server

Which MCP servers are FinChiefs'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 2026-10-28

← Back to FinChiefs

Whose server it is
  • Registry namecom.finchiefs/researchverified in the MCP registry

The registry name sits under finchiefs.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools8
  • Server calls itselffinchiefs
  • Server version1.0.1
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 897 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: read daily market highlights across published macro research; check how analyst consensus on gold has shifted; ask an AI assistant questions answered from daily research.
  • Checked on 5 of the 7 days it takes to judge reliability.

Once connected

  • For "read daily market highlights across published macro research", the likely first call is get_daily_digests.
  • Parameters are untyped or undescribed in 3 of 8 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.

Measured dailydaily checks: 5, the first on 2026-10-29
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 5 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring5 of the 7 daily checks it takes to print a share
  • Median first answer719 ms
  • Space in an agent's context≈ 2,433 tokensthe definitions of all its tools (8), which an agent carries on every turn
  • Tool definitionsA · 94 of 100
  • Typed results0 of 8 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 3 of 8

What an agent can do with it

  • can do · read daily market highlights across published macro research
  • can do · check how analyst consensus on gold has shifted
  • can do · ask an AI assistant questions answered from daily research

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 →

Tools it offers8 tools · read 2026-10-28
  • list_providers

    Research providers FinChiefs follows (banks, asset managers, central banks, multilaterals, independent researchers). Use the id to limit other tools to one provider.

  • list_categories

    Asset digest categories (gold, oil, us_bonds, eurusd, …) and macro categories (monetary_policy, geopolitics, …). Keys with has_daily_digest work with get_daily_digests; macro keys also filter search_macro_views and summarize_views.

  • summarize_views

    The overall picture from EVERY matching view in one small response: totals, up/down counts (asset views), how many providers lean each way, the busiest providers, a week-by-week trend, and the most-discussed assets or macro categories…

  • search_asset_views

    Individual directional views (up/down) on assets, with provider, date, horizon, rationale and a link to the source publication. Up/down tallies cover every match; items come in pages (offset / next_offset), spread across providers by…

  • search_macro_views

    Individual macro themes and drivers from provider research (growth, inflation, policy, fiscal, geopolitics, …), each with a description and a link to the source publication. Items come in pages (offset / next_offset), spread across…

  • search_research

    Research publications (articles, reports, podcasts) with title, provider, date, a short description and the link to the original. Ranked by how well the terms match (title matches count most), then newest; pages via offset / next_offset…

  • get_daily_digests

    Daily summaries written from all providers' views for a category (e.g. gold, oil, us_bonds, top macro themes, policy makers), with the day's up/down tallies. Good for how a view changed day by day. Category keys (has_daily_digest) come…

  • get_policy_signals

    Structured reads of central-bank and multilateral publications: decisions, stance (-2 dovish to +2 hawkish), guidance, conditions, speaker and forecasts, each with a link to the original. Newest first; pages via offset / next_offset.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "research": {
      "type": "http",
      "url": "https://finchiefs.com/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http finchiefs https://finchiefs.com/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://finchiefs.com/api/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.