fcc-broadband-mcp-server

Find Underserved Areas

fcc_find_underserved

Read-onlyIdempotent

Finds geographic areas with limited or no broadband coverage at a given speed threshold, ranked by unserved population. The core tool for BEAD program analysis and broadband equity research. Accepts a state abbreviation to narrow scope or runs nationwide. Defaults to rural areas where underservice is most concentrated. Data is from FCC Form 477 (as of June 2021).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum number of areas to return, ranked by unserved population (descending).
`state`	No	2-letter USPS state or territory code (e.g., "WY", "MS", "PR") to limit scope. An unrecognized code is rejected, not ignored. Omit for nationwide search — returns top areas only.
`speed_down`	No	Download speed threshold in Mbps for defining "underserved." 25 = FCC legacy standard. 100 = BEAD program standard.	25
`tech_filter`	No	Technology filter. "acfosw" = any wired or fixed wireless. "f" = fiber only. "c" = cable only.	acfosw
`geography_type`	No	Geographic granularity for results. "county" is most useful for policy analysis and BEAD eligibility. "cd" = congressional district. "place" = census-designated place. "cbsa" = metro area.	county
`min_unserved_pop`	No	Minimum population with no coverage to include. Defaults to 1, which keeps fully covered areas out of a ranking of underserved ones. Set to 0 to rank every area regardless of unserved population, or higher to drop small gaps (e.g., 500 keeps only areas with at least 500 unserved residents).
`urban_rural_filter`	No	Defaults to rural ("R") — where underservice is most concentrated. Use "U" to find underserved urban areas (digital redlining research). Set to "all" for both.	R

Output Schema

TableJSON Schema

Name	Required	Description
`cap`	No	The limit that was applied. Present when truncated.
`areas`	No	Ranked list of underserved areas.
`error`	No	Present when the call failed. Absent on success.
`shown`	No	Number of areas returned after applying the limit. Present when truncated.
`notice`	No	Guidance about the result set — how to broaden the filters when nothing matched, and how to narrow the query when the upstream scan hit its row ceiling. Absent when neither applies.
`truncated`	No	True when more areas matched than the limit returned. Absent when not truncated.
`scanRowCap`	No	Raw upstream row ceiling that bound the scan. Present only when scanTruncated is true.
`totalFound`	No	Total number of areas found before applying the limit filter.
`dataVintage`	No	Data vintage — Form 477 data as of June 2021.
`geographyType`	No	Geography type returned.
`scanTruncated`	No	True when the upstream row scan stopped at its ceiling before reaching the end of the matching data, so totalFound and the ranking cover only the portion that was scanned. Absent when the scan read every matching row.
`speedDownMbps`	No	Speed threshold used in Mbps.
`appliedFilters`	No	Filters applied to this query.
`urbanRuralFilter`	No	Urban/rural filter applied.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 20, 2026

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `no_areas_found`: No areas found matching the criteria after applying filters. `unknown_state`: The state input is two uppercase letters but is not a USPS state or territory abbreviation. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `unknown_state`: The state input is two uppercase letters but is not a USPS state or territory abbreviation. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "no_areas_found",
-  "unknown_state"
-]New value: +[
+  "unknown_state"
+]

Changed6 schema fields changedAug 25, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedInput schema / additionalProperties
```
Added value: +false
```

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedOutput schema / anyOf

Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "areas",
+      "geographyType",
+      "speedDownMbps",
+      "urbanRuralFilter",
+      "dataVintage",
+      "totalFound",
+      "appliedFilters"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

addedOutput schema / properties / error

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `no_areas_found`: No areas found matching the criteria after applying filters. `unknown_state`: The state input is two uppercase letters but is not a USPS state or territory abbreviation. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "no_areas_found",
+            "unknown_state"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}

removedOutput schema / required

Removed value: -[
-  "areas",
-  "geographyType",
-  "speedDownMbps",
-  "urbanRuralFilter",
-  "dataVintage",
-  "totalFound",
-  "appliedFilters"
-]

Changed6 schema fields changedAug 13, 2026

changedInput schema / properties / min_unserved_pop / default
```
Previous value: -0New value: +1
```

changedInput schema / properties / min_unserved_pop / description

Previous value: -"Minimum population with no coverage to include. Use to filter out very small areas (e.g., 500 filters areas with fewer than 500 unserved residents)."New value: +"Minimum population with no coverage to include. Defaults to 1, which keeps fully covered areas out of a ranking of underserved ones. Set to 0 to rank every area regardless of unserved population, or higher to drop small gaps (e.g., 500 keeps only areas with at least 500 unserved residents)."

changedInput schema / properties / state / description

Previous value: -"2-letter state code (e.g., \"WY\", \"MS\") to limit scope. Omit for nationwide search — returns top areas only."New value: +"2-letter USPS state or territory code (e.g., \"WY\", \"MS\", \"PR\") to limit scope. An unrecognized code is rejected, not ignored. Omit for nationwide search — returns top areas only."

changedOutput schema / properties / notice / description

Previous value: -"Recovery hint when no areas are found — suggests how to broaden the filters. Absent on successful results."New value: +"Guidance about the result set — how to broaden the filters when nothing matched, and how to narrow the query when the upstream scan hit its row ceiling. Absent when neither applies."

addedOutput schema / properties / scanRowCap

Added value: +{
+  "description": "Raw upstream row ceiling that bound the scan. Present only when scanTruncated is true.",
+  "type": "number"
+}

addedOutput schema / properties / scanTruncated

Added value: +{
+  "description": "True when the upstream row scan stopped at its ceiling before reaching the end of the matching data, so totalFound and the ranking cover only the portion that was scanned. Absent when the scan read every matching row.",
+  "type": "boolean"
+}

Changed1 schema field changedJul 2, 2026

addedOutput schema / properties / areas / items / properties / name

Added value: +{
+  "description": "Human-readable geography name if resolved (e.g., \"Pontotoc County, MS\").",
+  "type": "string"
+}

Changed3 schema fields changedJun 12, 2026

addedOutput schema / properties / cap

Added value: +{
+  "description": "The limit that was applied. Present when truncated.",
+  "type": "number"
+}

addedOutput schema / properties / shown

Added value: +{
+  "description": "Number of areas returned after applying the limit. Present when truncated.",
+  "type": "number"
+}

addedOutput schema / properties / truncated

Added value: +{
+  "description": "True when more areas matched than the limit returned. Absent when not truncated.",
+  "type": "boolean"
+}

Changed3 schema fields changedMay 30, 2026

addedOutput schema / properties / appliedFilters

Added value: +{
+  "additionalProperties": false,
+  "description": "Filters applied to this query.",
+  "properties": {
+    "geographyType": {
+      "description": "Geographic granularity queried.",
+      "type": "string"
+    },
+    "minUnservedPop": {
+      "description": "Minimum unserved population filter applied.",
+      "type": "number"
+    },
+    "speedDownMbps": {
+      "description": "Download speed threshold in Mbps.",
+      "type": "number"
+    },
+    "state": {
+      "description": "State abbreviation filter applied. Absent for nationwide searches.",
+      "type": "string"
+    },
+    "techFilter": {
+      "description": "Technology filter applied.",
+      "type": "string"
+    },
+    "urbanRuralFilter": {
+      "description": "Urban/rural filter applied.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "geographyType",
+    "speedDownMbps",
+    "techFilter",
+    "urbanRuralFilter",
+    "minUnservedPop"
+  ],
+  "type": "object"
+}

changedOutput schema / properties / notice / description

Previous value: -"Recovery hint when no areas are found."New value: +"Recovery hint when no areas are found — suggests how to broaden the filters. Absent on successful results."

changedOutput schema / required

Previous value: -[
-  "areas",
-  "totalFound",
-  "geographyType",
-  "speedDownMbps",
-  "urbanRuralFilter",
-  "dataVintage"
-]New value: +[
+  "areas",
+  "geographyType",
+  "speedDownMbps",
+  "urbanRuralFilter",
+  "dataVintage",
+  "totalFound",
+  "appliedFilters"
+]

First observedMay 29, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Beyond annotations (readOnlyHint, idempotentHint), the description adds valuable behavioral context: data comes from FCC Form 477 dated June 2021, the tool defaults to rural areas, and nationwide search returns top areas only. These details extend the safety and expectation profile without contradicting the annotations.

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

Conciseness5/5

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

Four sentences with no filler. The first sentence states the core purpose with ranking; the second establishes domain importance; the third explains scope; the fourth notes the rural default and data vintage. Information is front-loaded and every sentence earns its place.

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 7-parameter tool with a rich schema and output schema, the description provides enough high-level context (purpose, scope, defaults, data source) to guide correct invocation. It doesn't enumerate all parameters, but the schema shoulders that burden. A slightly fuller example of BEAD usage (e.g., speed_down=100) would push it to 5.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds color around 'state' (narrow scope or nationwide) and 'urban_rural_filter' (defaults rural), but these details are already present in the schema descriptions. It does not meaningfully elevate understanding beyond the structured fields.

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

Purpose5/5

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

The description uses a specific verb ('Finds') with a clear resource ('geographic areas with limited or no broadband coverage at a given speed threshold') and a distinct ranking criterion. It also labels itself 'The core tool for BEAD program analysis and broadband equity research,' which differentiates it from siblings like fcc_search_availability or fcc_get_coverage_summary even without naming them.

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

Usage Guidelines4/5

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

It gives clear context for when to use the tool ('core tool for BEAD program analysis and broadband equity research') and describes scope options (state vs. nationwide, rural default). However, it does not explicitly state when not to use it or name alternative tools, so it stops short of full exclusion guidance.

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

All fcc-broadband-mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.