
Morning Brief API Hub MCP server
Which MCP servers are Morning Brief API Hub'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
- Registry namelink.morningbrief/bridgesverified in the MCP registry
The registry name sits under morningbrief.link. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-28
- Tools10
- Server calls itselfbridges
- Server version1.0.0
- Protocol version2024-11-05
On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 90 ms.
- Its tools do none of the product's use cases we checked: Pull daily grain cash bids by region into an app; Compare public company financials across SEC filings; Look up farmland values and cash rents by county.
- Checked on 6 of the 7 days it takes to judge reliability.
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 scoreafter a weeka score needs 7 daily checks: 6 so far
- What an agent can do with it0 of 3 use cases
- Answeredmeasuring6 of the 7 daily checks it takes to print a share
- Median first answer83 ms
- Space in an agent's context≈ 2,891 tokensthe definitions of all its tools (10), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 10 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- cannot · Pull daily grain cash bids by region into an app
- cannot · Compare public company financials across SEC filings
- cannot · Look up farmland values and cash rents by county
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_bridgesSearch US bridges in the FHWA National Bridge Inventory. Scope with state, county (3-digit FIPS code), and/or condition (Good/Fair/Poor); optional filters: posting_status (open/posted/closed/not_yet_open), owner_code, scour_critical…
get_bridgeGet one bridge by its FHWA structure number (Item 8). Structure numbers are unique within a state; pass state to be exact. Returns the full decoded record.
list_bridges_in_countyList bridges in one county (state + 3-digit FIPS county code), paged.
get_worst_bridgesThe worst-rated bridges in a state (condition = Poor), ordered by lowest component rating then age. State is required. Use for 'worst bridges in X' questions.
list_posted_or_closed_bridgesBridges in a state that are load-posted or closed to traffic (NBI Item 41 status P/R/K), worst condition first. Relevant for routing and heavy-haul feasibility — but per FHWA, NBI data must not be used as the sole source for route…
find_low_clearance_bridgesBridges in a state whose vertical clearance is at or below max_height_m (or max_height_ft in feet — pass one, not both). Default clearance is over the roadway on the bridge (NBI Item 10); set under=true for the clearance under the bridge…
get_state_summaryBridge summary for one state: total bridges, counts by condition (Good/Fair/Poor), posted and closed counts, scour-critical count, average year built, total deck area. Without a state, returns per-state totals with condition counts for…
get_county_summariesPer-county bridge counts for a state, with Poor-condition and posted/closed counts per county.
find_bridges_nearbyBridges near a point, nearest first. Pass lat/lon in decimal degrees; radius_km defaults to 10 (max 500). Each returned bridge carries distance_km. Bridges with no coordinates are excluded. Unlike the state-scoped tools, this one takes no…
screen_corridorScreen a corridor for a vehicle profile: pass a route polyline as points (array of {lat, lon} objects tracing the actual road — submit a real route trace, not city points) plus a vehicle height and weight, and get back every bridge near…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"bridges": {
"type": "http",
"url": "https://bridges.morningbrief.link/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http morningbrief https://bridges.morningbrief.link/mcpclaude.ai, ChatGPT and other clients: add https://bridges.morningbrief.link/mcp as a custom connector in the settings.
- link.morningbrief/edgaranswers, 5 toolsverified in the MCP registry
- link.morningbrief/farmlandanswers, 3 toolsverified in the MCP registry
- link.morningbrief/magpienot asked yetverified in the MCP registry
- link.morningbrief/weathernot asked yetverified in the MCP registry
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.
Cookies
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.