Skip to main content
Glama

browser-compat-mcp-server

by io.github.cyanheads
OverviewDiscussionsAdmin

Browsercompat Compare Support

browsercompat_compare_support
Read-onlyIdempotent

Compute whether a set of web features clears an explicit browserslist target query. Every call evaluates the whole query: each feature gets a verdict, the count of failing targets, and its own evaluated and unevaluated target counts with the share of tracked traffic each covers. The target rows behind those numbers — which release each target maps to, which targets were not evaluated and why, and the failing and unevaluated targets of each feature — cover at most ten query targets per call; page through them with target_offset and target_limit, and the verdicts, coverage, and totals stay identical on every page. A target counts as evaluated only where compatibility data was read for it, so a feature clears only when every target in the query was evaluated and supports it, and is inconclusive otherwise — a query that includes a browser with no compatibility data, as "defaults" does, never clears.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
resolveNoWhen true, an entry that is neither a key nor an id falls back to the search index, such as "Container queries (size)" or "Element.prototype.animate". Its best exact matches are accepted only when they name one feature: a single key resolves to that key and gets a verdict, several keys of one web-features feature resolve to the feature as verdict ambiguous with compat_keys, and matches spanning two features are a miss. Off by default so a typo returns a miss you can correct rather than a confident answer about the wrong feature.
targetsYesA browserslist query, for example "defaults" or "> 0.5%, last 2 versions", 1 to 500 characters. Required: with no query browserslist would read config from the process working directory rather than from your project.
featuresYesUp to 20 entries, each a browser-compat-data key such as css.selectors.has or a web-features id such as has, 1 to 200 characters. An empty or longer entry is rejected against this schema; a whitespace-only entry returns invalid_feature_input. Call browsercompat_search_features first for any entry whose key you do not already know.
target_limitNoHow many query targets this page covers, 1 to 10. It bounds every list of target rows in the response and never the evaluation: verdicts, coverage, and totals always describe the whole query.
target_offsetNoZero-based position in the target list of the query at which this page of target rows starts. Pass the nextOffset of the previous response to continue. An offset at or past the number of targets returns the whole-query verdicts and totals with no target rows.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
capNoThe target_limit that was applied.
errorNoPresent when the call failed. Absent on success.
shownNoNumber of query targets this page covers.
resultsNoPer-feature verdicts and totals over the whole query, each with its own target rows for this page.
all_clearNoTrue only when every feature clears, which requires every target in the query to have been evaluated for it.
truncatedNoTrue when more query targets remain past this page.
nextOffsetNoThe target_offset of the next page. Present only while targets remain past this page.
query_echoNoThe targets query as the server parsed it.
totalCountNoNumber of targets the query resolved to, across every page.
attributionNoRequired attribution for the caniuse-derived coverage figures in this response.
data_versionNoVintage of each bundled dataset behind this answer.
offsetNoticeNoWhy this page carries no target rows, and the offsets that do.
uncheckedNoticeNoHow many of the query targets were not evaluated for every compared feature, the agents they belong to, and their combined usage share.
targets_resolvedNoThe mapping inventory for the query targets on this page: each target that maps onto a browser-compat-data release, and whether it was evaluated. A target with no mapping appears only in unchecked_targets.
unchecked_targetsNoThe query targets on this page that were not evaluated for every compared feature, each with the reason.
comparable_featuresNoHow many entries in features were compared against the targets. A miss or an ambiguous entry is not comparable; at 0 nothing was evaluated.
targets_resolved_totalNoQuery targets that map onto a browser-compat-data release, across every page.
evaluated_targets_totalNoQuery targets evaluated for every compared feature, across every page. evaluated_targets_total plus unchecked_targets_total is the number of targets in the query.
target_coverage_percentNoShare of tracked global traffic covered by the targets evaluated for every compared feature; 0 when no feature was comparable.
unchecked_targets_totalNoQuery targets not evaluated for every compared feature, across every page.
unchecked_coverage_percentNoShare of tracked global traffic covered by the targets counted in unchecked_targets_total.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed33 schema fields changed
    • changedInput schema / properties / resolve / description
      Previous value: -"When true, an entry that is neither a key nor an id falls back to the search index, such as \"Container queries\" or \"Element.prototype.animate\". Its best exact matches are accepted only when they name one feature: a single key resolves to that key and gets a verdict, several keys of one web-features feature resolve to the feature as verdict ambiguous with compat_keys, and matches spanning two features are a miss. Off by default so a typo returns a miss you can correct rather than a confident answer about the wrong feature."New value: +"When true, an entry that is neither a key nor an id falls back to the search index, such as \"Container queries (size)\" or \"Element.prototype.animate\". Its best exact matches are accepted only when they name one feature: a single key resolves to that key and gets a verdict, several keys of one web-features feature resolve to the feature as verdict ambiguous with compat_keys, and matches spanning two features are a miss. Off by default so a typo returns a miss you can correct rather than a confident answer about the wrong feature."
    • addedInput schema / properties / target_limit
      Added value: +{
+  "default": 10,
+  "description": "How many query targets this page covers, 1 to 10. It bounds every list of target rows in the response and never the evaluation: verdicts, coverage, and totals always describe the whole query.",
+  "maximum": 10,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / target_offset
      Added value: +{
+  "default": 0,
+  "description": "Zero-based position in the target list of the query at which this page of target rows starts. Pass the nextOffset of the previous response to continue. An offset at or past the number of targets returns the whole-query verdicts and totals with no target rows.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}
    • changedOutput schema / anyOf
      Previous value: -[
-  {
-    "not": {
-      "required": [
-        "error"
-      ]
-    },
-    "required": [
-      "query_echo",
-      "targets_resolved",
-      "unchecked_targets",
-      "target_coverage_percent",
-      "unchecked_coverage_percent",
-      "results",
-      "all_clear",
-      "data_version",
-      "totalCount",
-      "attribution"
-    ]
-  },
-  {
-    "required": [
-      "error"
-    ]
-  }
-]New value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "query_echo",
+      "comparable_features",
+      "targets_resolved",
+      "targets_resolved_total",
+      "evaluated_targets_total",
+      "unchecked_targets",
+      "unchecked_targets_total",
+      "target_coverage_percent",
+      "unchecked_coverage_percent",
+      "results",
+      "all_clear",
+      "data_version",
+      "totalCount",
+      "shown",
+      "cap",
+      "truncated",
+      "attribution"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]
    • changedOutput schema / properties / all_clear / description
      Previous value: -"True only when every feature clears and unchecked_targets is empty."New value: +"True only when every feature clears, which requires every target in the query to have been evaluated for it."
    • addedOutput schema / properties / cap
      Added value: +{
+  "description": "The target_limit that was applied.",
+  "type": "number"
+}
    • addedOutput schema / properties / comparable_features
      Added value: +{
+  "description": "How many entries in features were compared against the targets. A miss or an ambiguous entry is not comparable; at 0 nothing was evaluated.",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}
    • addedOutput schema / properties / evaluated_targets_total
      Added value: +{
+  "description": "Query targets evaluated for every compared feature, across every page. evaluated_targets_total plus unchecked_targets_total is the number of targets in the query.",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}
    • addedOutput schema / properties / nextOffset
      Added value: +{
+  "description": "The target_offset of the next page. Present only while targets remain past this page.",
+  "type": "number"
+}
    • addedOutput schema / properties / offsetNotice
      Added value: +{
+  "description": "Why this page carries no target rows, and the offsets that do.",
+  "type": "string"
+}
    • changedOutput schema / properties / results / description
      Previous value: -"Per-feature verdicts against the resolved targets."New value: +"Per-feature verdicts and totals over the whole query, each with its own target rows for this page."
    • addedOutput schema / properties / results / items / properties / evaluated_coverage_percent
      Added value: +{
+  "description": "Share of tracked global traffic the targets evaluated for this feature cover.",
+  "type": "number"
+}
    • addedOutput schema / properties / results / items / properties / evaluated_total
      Added value: +{
+  "description": "Query targets this feature has compatibility data for, across the whole query.",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}
    • changedOutput schema / properties / results / items / properties / failing_targets / description
      Previous value: -"Every resolved target that failed, with the verdict that caused it."New value: +"The failing targets among the query targets on this page, with the verdict that caused each. Empty on a page that holds none even when failing_total is above zero."
    • addedOutput schema / properties / results / items / properties / failing_total
      Added value: +{
+  "description": "Failing targets across the whole query. Present when the feature was compared, as are the five fields after it.",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}
    • addedOutput schema / properties / results / items / properties / unchecked_coverage_percent
      Added value: +{
+  "description": "Share of tracked global traffic the targets not evaluated for this feature cover.",
+  "type": "number"
+}
    • addedOutput schema / properties / results / items / properties / unchecked_targets
      Added value: +{
+  "description": "The targets not evaluated for this feature among the query targets on this page, each with its reason.",
+  "items": {
+    "additionalProperties": false,
+    "description": "A target this feature was not evaluated against.",
+    "properties": {
+      "agent": {
+        "description": "browserslist agent id.",
+        "type": "string"
+      },
+      "reason": {
+        "description": "no_bcd_browser when the agent has no browser-compat-data counterpart, unknown_version when the token maps to no release, no_bcd_data when a compared feature records nothing for that browser, no_comparable_feature when every entry in features was a miss or ambiguous so nothing was compared.",
+        "enum": [
+          "no_bcd_browser",
+          "unknown_version",
+          "no_bcd_data",
+          "no_comparable_feature"
+        ],
+        "type": "string"
+      },
+      "usage_percent": {
+        "description": "Share of tracked global traffic this target covers.",
+        "type": "number"
+      },
+      "version_token": {
+        "description": "Version token browserslist produced for that agent.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "agent",
+      "version_token",
+      "reason",
+      "usage_percent"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • addedOutput schema / properties / results / items / properties / unchecked_total
      Added value: +{
+  "description": "Query targets not evaluated for this feature, across the whole query. evaluated_total plus unchecked_total is the number of targets in the query.",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}
    • changedOutput schema / properties / results / items / properties / verdict / description
      Previous value: -"clears only when every resolved target is supported; inconclusive when a target could not be evaluated, including when no target resolved at all; ambiguous when the id spans more than one compat key."New value: +"Judged over the whole query, never over one page. fails when any evaluated target does not support the feature; inconclusive when nothing failed but at least one target in the query was not evaluated for this feature, including when none was; clears only when every target in the query was evaluated and supports it; miss when the entry did not resolve; ambiguous when the id spans more than one compat key or owns none."
    • addedOutput schema / properties / shown
      Added value: +{
+  "description": "Number of query targets this page covers.",
+  "type": "number"
+}
    • changedOutput schema / properties / target_coverage_percent / description
      Previous value: -"Share of tracked global traffic the evaluated targets cover."New value: +"Share of tracked global traffic covered by the targets evaluated for every compared feature; 0 when no feature was comparable."
    • changedOutput schema / properties / targets_resolved / description
      Previous value: -"Every browserslist token that was evaluated."New value: +"The mapping inventory for the query targets on this page: each target that maps onto a browser-compat-data release, and whether it was evaluated. A target with no mapping appears only in unchecked_targets."
    • addedOutput schema / properties / targets_resolved / items / properties / evaluated
      Added value: +{
+  "description": "True when every compared feature has compatibility data for this target. False when at least one compared feature records nothing for its browser, or when no feature in the call was comparable — the target then also appears in unchecked_targets. Mapping onto a release is not evaluation.",
+  "type": "boolean"
+}
    • changedOutput schema / properties / targets_resolved / items / required
      Previous value: -[
-  "agent",
-  "version_token",
-  "bcd_browser",
-  "bcd_version",
-  "bcd_release_index"
-]New value: +[
+  "agent",
+  "version_token",
+  "bcd_browser",
+  "bcd_version",
+  "bcd_release_index",
+  "evaluated"
+]
    • addedOutput schema / properties / targets_resolved_total
      Added value: +{
+  "description": "Query targets that map onto a browser-compat-data release, across every page.",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}
    • changedOutput schema / properties / totalCount / description
      Previous value: -"Number of feature results returned."New value: +"Number of targets the query resolved to, across every page."
    • addedOutput schema / properties / truncated
      Added value: +{
+  "description": "True when more query targets remain past this page.",
+  "type": "boolean"
+}
    • changedOutput schema / properties / uncheckedNotice / description
      Previous value: -"Names the target agents that were not evaluated and their combined usage share."New value: +"How many of the query targets were not evaluated for every compared feature, the agents they belong to, and their combined usage share."
    • changedOutput schema / properties / unchecked_coverage_percent / description
      Previous value: -"Share of tracked global traffic the unevaluated targets cover."New value: +"Share of tracked global traffic covered by the targets counted in unchecked_targets_total."
    • changedOutput schema / properties / unchecked_targets / description
      Previous value: -"Every target the server declined to claim a verdict for, with the reason."New value: +"The query targets on this page that were not evaluated for every compared feature, each with the reason."
    • changedOutput schema / properties / unchecked_targets / items / properties / reason / description
      Previous value: -"no_bcd_browser when the agent has no counterpart, unknown_version when the token maps to no release, no_bcd_data when a feature records nothing for that browser."New value: +"no_bcd_browser when the agent has no browser-compat-data counterpart, unknown_version when the token maps to no release, no_bcd_data when a compared feature records nothing for that browser, no_comparable_feature when every entry in features was a miss or ambiguous so nothing was compared."
    • changedOutput schema / properties / unchecked_targets / items / properties / reason / enum
      Previous value: -[
-  "no_bcd_browser",
-  "unknown_version",
-  "no_bcd_data"
-]New value: +[
+  "no_bcd_browser",
+  "unknown_version",
+  "no_bcd_data",
+  "no_comparable_feature"
+]
    • addedOutput schema / properties / unchecked_targets_total
      Added value: +{
+  "description": "Query targets not evaluated for every compared feature, across every page.",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}
  2. Changed2 schema fields changed
    • changedInput schema / properties / resolve / description
      Previous value: -"When true, fall back to the search index and accept its single unambiguous top hit for each entry. Off by default so a typo returns a miss you can correct rather than a confident answer about the wrong feature."New value: +"When true, an entry that is neither a key nor an id falls back to the search index, such as \"Container queries\" or \"Element.prototype.animate\". Its best exact matches are accepted only when they name one feature: a single key resolves to that key and gets a verdict, several keys of one web-features feature resolve to the feature as verdict ambiguous with compat_keys, and matches spanning two features are a miss. Off by default so a typo returns a miss you can correct rather than a confident answer about the wrong feature."
    • changedOutput schema / properties / results / items / properties / resolved_as / anyOf
      Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "baseline_id": {
-        "description": "The web-features id this resolved to, or null when no web-features entry covers the key.",
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "bcd_key": {
-        "description": "The single browser-compat-data key this resolved to, or null when the web-features id spans more than one key.",
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "input": {
-        "description": "The feature string as the caller sent it, trimmed.",
-        "type": "string"
-      },
-      "resolved_via": {
-        "description": "Which step of the resolution order matched: bcd_key or web_features_id for an exact match, web_features_id_normalized when it matched only after lowercasing, redirect when the input pointed to a browser-compat-data entry that has moved or split, or search when resolve was true and the search index accepted a single unambiguous top hit — treat a search match as a best guess, not a confirmed key.",
-        "enum": [
-          "bcd_key",
-          "web_features_id",
-          "web_features_id_normalized",
-          "redirect",
-          "search"
-        ],
-        "type": "string"
-      }
-    },
-    "required": [
-      "input",
-      "bcd_key",
-      "baseline_id",
-      "resolved_via"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "baseline_id": {
+        "description": "The web-features id this resolved to, or null when no web-features entry covers the key.",
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "bcd_key": {
+        "description": "The single browser-compat-data key this resolved to, or null when the web-features id spans more than one key.",
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "input": {
+        "description": "The feature string as the caller sent it, trimmed.",
+        "type": "string"
+      },
+      "resolved_via": {
+        "description": "Which step of the resolution order matched: bcd_key or web_features_id for an exact match, web_features_id_normalized when it matched only after lowercasing, redirect when the input pointed to a browser-compat-data entry that has moved or split, or search when resolve was true and the best exact matches in the search index all named one feature or key — treat a search match as a best guess, not a confirmed key.",
+        "enum": [
+          "bcd_key",
+          "web_features_id",
+          "web_features_id_normalized",
+          "redirect",
+          "search"
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "input",
+      "bcd_key",
+      "baseline_id",
+      "resolved_via"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already mark it read-only, idempotent and closed-world, and the description adds substantial behavioral detail on top: pagination never changes verdicts/coverage/totals, a feature clears only when every target was evaluated and supports it, and a query containing a browser with no compat data (like 'defaults') never clears. This is exactly the kind of non-obvious semantics an agent needs.

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

Conciseness4/5

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

Front-loaded with the core purpose in sentence one, then layered semantics. It is dense but nearly every clause carries information; a small amount of overlap with the schema on page stability keeps it from a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists, yet the description still conveys the decisive semantics (evaluated vs unevaluated, inconclusive, clears-only-if-all-targets-evaluated). With annotations, a full parameter schema and an output schema, nothing an agent needs to call this correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description reinforces key parameter behavior — paging via target_offset/target_limit, the ten-target cap, and nextOffset continuation. It adds invariant-level meaning rather than merely restating field docs.

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?

States a precise verb and resource — computing whether a feature set clears an explicit browserslist query — and the word 'explicit' plus the query-based framing distinguishes it from the baseline-checking sibling. An agent can tell what it does and roughly how it differs from a fixed-baseline tool without opening a schema.

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?

Gives real usage context: call browsercompat_search_features first for unknown keys, and resolve is off by default so a typo yields a miss you can correct. It also explains pagination procedure. It stops short of naming when to prefer this over browsercompat_check_baseline or get_feature.

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

All browser-compat-mcp-server toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources