protogrid

Search / fi.brighter/brighter

Brighter

R0· no sign-in

Browse, backtest and write rule-based portfolios of tokenized US stocks.

v1.0.0 · active · website · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality83good
Trust83of 100
Uptime, 30 days100%
Latency p50604 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "brighter": {
      "type": "http",
      "url": "https://mcp.brighter.fi/mcp"
    }
  }
}
claude mcp add --transport http brighter https://mcp.brighter.fi/mcp
[mcp_servers.brighter]
url = "https://mcp.brighter.fi/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "brighter": {
      "type": "remote",
      "url": "https://mcp.brighter.fi/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "brighter": {
      "type": "http",
      "url": "https://mcp.brighter.fi/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=brighter&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLmJyaWdodGVyLmZpL21jcCJ9"
}
{
  "servers": {
    "brighter": {
      "type": "http",
      "url": "https://mcp.brighter.fi/mcp"
    }
  }
}
{
  "mcpServers": {
    "brighter": {
      "httpUrl": "https://mcp.brighter.fi/mcp"
    }
  }
}
extensions:
  "brighter":
    enabled: true
    name: "brighter"
    type: streamable_http
    uri: "https://mcp.brighter.fi/mcp"
    timeout: 300

Quality 83 / 100good

protocol88 · weight 25
  • pass
    protocol.modernsupports 2026-07-28 (server/discover)
  • pass
    protocol.statelessanswers without a session
  • pass
    protocol.transportstreamable HTTP
  • warn
    protocol.list_ttltools/list carries no ttlMs, so clients re-fetch it
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene71 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • fail
    tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: backtest_strategy (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); backtest_code (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); dsl_reference (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
  • pass
    tools.token_costabout 1,453 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability100 · weight 15
  • pass
    stability.changesno tool changes in 30 days
  • pass
    stability.rug_pullno tool changed its meaning under the same name
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

11 tools, about 1,453 tokens to load them all · tool set 719db6c20119 · checked 2026-10-20 10:35 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 83 / 100

no-repository
provenance55
liveness100
freshness100
hygiene80

+dns-namespace +website +reachable +uptime-100% +updated-20d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://mcp.brighter.fi/mcp streamable-httpnoneyes100%604 ms2026-07-28, 2025-11-25, 2025-06-18, 2025-03-262026-10-20

Tools (11)

asset_historyDaily closing prices for one asset over a calendar year, for checking a rule's premise against what actually happened.
backtest_codeRun a strategy you have written against real market history and return its figures. This is a real backtest against real prices — not a simulation and not cached per call — so run it deliberately, after check_strategy passes. Returns metrics only, never the curve.
backtest_strategyRun a published strategy over real market history with parameters of your choosing. Returns its figures against its benchmark. Values outside a parameter's range are snapped into it. This is a real backtest, so make each one count.
check_strategyCheck a strategy written in Brighter's language: syntax, semantics, and whether every ticker it names is one Brighter can actually trade. Returns the faults with their line and column. Costs nothing and calls nothing upstream — check before you backtest.
dsl_referenceHow to write a Brighter strategy: the language's blocks, indentation rules, indicators and limits. Read this before writing any rule — the language is small and specific, and guessing its syntax wastes a turn.
find_assetsSearch the assets a Brighter strategy can hold — tokenized US stocks, ETFs and T-bills. A rule may only name a ticker that appears here.
format_strategyRewrite a strategy in the language's canonical form — the spelling Studio's editor shows. Useful for checking that what you wrote means what you think it means.
get_allocationWhat a published strategy's rule holds right now, in basis points of the portfolio. This is the live target, computed from the latest close.
get_strategyOne strategy in full: what its rule does, the parameters you can tune with their ranges and defaults, every asset it can hold, and its benchmark. Use the parameter keys with backtest_strategy.
list_strategiesList the strategies published on brighter.fi, newest or best-performing first. Each carries its rebalance cadence, the assets it can hold, and its return over the chosen period against its benchmark. Strategies that can hold leveraged or inverse funds are excluded unless asked for.
strategy_schemaThe JSON schema for a strategy as an object, for when you would rather build the rule tree than write the text. check_strategy and backtest_code both accept text, which is usually easier.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "fi.brighter/brighter",
  "title": "Brighter",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.brighter.fi/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://brighter.fi",
  "description": "Browse, backtest and write rule-based portfolios of tokenized US stocks."
}