mcp-claudinho

Prediction-market signal

get_market_signal

Read-only

Fetch read-only prediction-market signals by match ID, team code, or date to get market-implied percentages with attribution for pre-match and live informational use.

Instructions

Read-only prediction-market signals for a match (by id), a team's current-or-next fixture, or a date (default: today). Returns market-implied percentages with attribution; complete:false means the provider read was incomplete, not that no signal exists; partial says the same of the fixture read behind the answer (the provider sent fixture records that could not be used). Shown only before and during a match: finished matches have no market read. Informational only: relay the numbers factually; do not add betting, trading, or 'value' advice, and do not invent links.

Input Schema

Name	Required	Description
`tz`	No	IANA timezone for kickoff times, e.g. America/Mexico_City
`date`	No	Date as YYYY-MM-DD (default: today) for all that day's signals
`lang`	No	Locale for dates, list titles, match status and stage words, a match timeline's kind words (Goal, Yellow card…), the empty and outage sentences, provider attribution, and commentary: en, es, pt or fr (no other value is supported). Without it, or when it is empty, the server's CLAUDINHO_LANG when that is exactly one of the four, else en. The market copy, a few notes and the disclaimer stay English
`team`	No	3-letter team code, e.g. MEX; resolves to the team's in-play match when one is live, else their next fixture
`flavor`	No	Commentary flair: off, subtle, full (default: full)
`matchId`	No	Match id (most specific)
`competition`	No	The competition: an alias such as premier-league, or an ESPN slug such as eng.1 (list_competitions lists the aliases). Without it: the server's CLAUDINHO_COMPETITION, else the user's saved choice (claudinho follow); with none, the answer is noCompetition

Output Schema

Name	Required	Description
`date`	No
`team`	No
`count`	No
`signal`	No
`matchId`	No
`partial`	No	Present when the provider sent records that could not be used: what is returned is what was read, and may not be the whole answer (absence is not elimination). omitted is how many provider records were left out, when known; they may have lain outside what was asked for, so the count is a bound, not a loss
`signals`	No
`complete`	No	False when the market provider did not complete every relevant read
`degraded`	No
`truncated`	No
`competition`	No	The competition this answer is for: its ESPN slug, its alias, its name, where the choice came from (flag: the competition argument; env: the server's CLAUDINHO_COMPETITION; saved: the user's saved choice, claudinho follow), and experimental for a slug the supported table does not hold; null with noCompetition when nothing is chosen
`unknownTeam`	No	Present (true) when the roster the competition has holds no team by that name: the bundled nations on the World Cup; the table read whole and the next 14 days' fixtures elsewhere (a claim about that evidence, not the whole competition: a club out in a qualifying round is in no table). Never stated when the table or the span could not be read whole
`unsupported`	No	Present (true) when this is not available for this competition yet; an empty result then means "unsupported", not "none found"
`inapplicable`	No	Present (true) when this competition has no such thing at all (a league season with no knockout tie has no knockout tree)
`noCompetition`	No	Present (true) when no competition is chosen (no competition argument, no server CLAUDINHO_COMPETITION, no saved choice): nothing was read, competition is null, and the text says what to do (pass competition, or the user runs claudinho follow <alias>)
`rosterEvidence`	No	With unknownTeam: the evidence it rests on, the competition's table and span (table) or the World Cup's bundled nations (bundle)
`betweenEditions`	No	Present when the competition is between editions: the edition named by label ended on ended (the provider's calendar day, YYYY-MM-DD, the season end it states), and nothing in the read is scheduled or in play
`rosterIncomplete`	No	Present (true) when the competition's roster could not be read whole and the name could not be resolved without it (no match, or only by a code or a partial name); not an outage: ask with the club's full name
`informationalOnly`	Yes
`responseTruncated`	No
`responseTruncation`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.13.1Oct 30, 2026

changedInput schema / properties / lang / description

Previous value: -"Locale for dates, list titles, match status and stage words, a match timeline's kind words (Goal, Yellow card…), the empty and outage sentences, provider attribution, and commentary: en, es, pt, fr (the market copy, a few notes and the disclaimer stay English; other locales fall back to en)"New value: +"Locale for dates, list titles, match status and stage words, a match timeline's kind words (Goal, Yellow card…), the empty and outage sentences, provider attribution, and commentary: en, es, pt or fr (no other value is supported). Without it, or when it is empty, the server's CLAUDINHO_LANG when that is exactly one of the four, else en. The market copy, a few notes and the disclaimer stay English"

Changed12 schema fields changedv0.12.0Oct 18, 2026

addedInput schema / properties / competition

Added value: +{
+  "description": "The competition: an alias such as premier-league, or an ESPN slug such as eng.1 (list_competitions lists the aliases). Without it: the server's CLAUDINHO_COMPETITION, else the user's saved choice (claudinho follow); with none, the answer is noCompetition",
+  "type": "string"
+}

changedInput schema / properties / lang / description

Previous value: -"Locale for dates, provider attribution, and commentary: en, es, pt, fr (the summary scaffold stays English; other locales fall back to en)"New value: +"Locale for dates, list titles, match status and stage words, a match timeline's kind words (Goal, Yellow card…), the empty and outage sentences, provider attribution, and commentary: en, es, pt, fr (the market copy, a few notes and the disclaimer stay English; other locales fall back to en)"

changedInput schema / properties / team / description

Previous value: -"3-letter team code, e.g. MEX — resolves to the team's in-play match when one is live, else their next fixture"New value: +"3-letter team code, e.g. MEX; resolves to the team's in-play match when one is live, else their next fixture"

addedOutput schema / properties / betweenEditions

Added value: +{
+  "additionalProperties": false,
+  "description": "Present when the competition is between editions: the edition named by label ended on ended (the provider's calendar day, YYYY-MM-DD, the season end it states), and nothing in the read is scheduled or in play",
+  "properties": {
+    "ended": {
+      "type": "string"
+    },
+    "label": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "ended"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / competition

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "properties": {
+        "alias": {
+          "type": "string"
+        },
+        "chosenBy": {
+          "enum": [
+            "flag",
+            "env",
+            "saved"
+          ],
+          "type": "string"
+        },
+        "experimental": {
+          "const": true,
+          "type": "boolean"
+        },
+        "name": {
+          "type": "string"
+        },
+        "slug": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "slug",
+        "name",
+        "chosenBy"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "The competition this answer is for: its ESPN slug, its alias, its name, where the choice came from (flag: the competition argument; env: the server's CLAUDINHO_COMPETITION; saved: the user's saved choice, claudinho follow), and experimental for a slug the supported table does not hold; null with noCompetition when nothing is chosen"
+}

addedOutput schema / properties / inapplicable

Added value: +{
+  "const": true,
+  "description": "Present (true) when this competition has no such thing at all (a league season with no knockout tie has no knockout tree)",
+  "type": "boolean"
+}

addedOutput schema / properties / noCompetition

Added value: +{
+  "const": true,
+  "description": "Present (true) when no competition is chosen (no competition argument, no server CLAUDINHO_COMPETITION, no saved choice): nothing was read, competition is null, and the text says what to do (pass competition, or the user runs claudinho follow <alias>)",
+  "type": "boolean"
+}

addedOutput schema / properties / partial

Added value: +{
+  "additionalProperties": false,
+  "description": "Present when the provider sent records that could not be used: what is returned is what was read, and may not be the whole answer (absence is not elimination). omitted is how many provider records were left out, when known; they may have lain outside what was asked for, so the count is a bound, not a loss",
+  "properties": {
+    "omitted": {
+      "exclusiveMinimum": 0,
+      "type": "integer"
+    }
+  },
+  "type": "object"
+}

addedOutput schema / properties / rosterEvidence

Added value: +{
+  "description": "With unknownTeam: the evidence it rests on, the competition's table and span (table) or the World Cup's bundled nations (bundle)",
+  "enum": [
+    "table",
+    "bundle"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / rosterIncomplete

Added value: +{
+  "const": true,
+  "description": "Present (true) when the competition's roster could not be read whole and the name could not be resolved without it (no match, or only by a code or a partial name); not an outage: ask with the club's full name",
+  "type": "boolean"
+}

addedOutput schema / properties / unknownTeam

Added value: +{
+  "const": true,
+  "description": "Present (true) when the roster the competition has holds no team by that name: the bundled nations on the World Cup; the table read whole and the next 14 days' fixtures elsewhere (a claim about that evidence, not the whole competition: a club out in a qualifying round is in no table). Never stated when the table or the span could not be read whole",
+  "type": "boolean"
+}

addedOutput schema / properties / unsupported

Added value: +{
+  "const": true,
+  "description": "Present (true) when this is not available for this competition yet; an empty result then means \"unsupported\", not \"none found\"",
+  "type": "boolean"
+}

Changed5 schema fields changedv0.10.0Sep 15, 2026

addedOutput schema / properties / complete

Added value: +{
+  "description": "False when the market provider did not complete every relevant read",
+  "type": "boolean"
+}

addedOutput schema / properties / count
```
Added value: +{
+  "type": "number"
+}
```
addedOutput schema / properties / responseTruncated
```
Added value: +{
+  "type": "boolean"
+}
```
addedOutput schema / properties / responseTruncation
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / truncated
```
Added value: +{
+  "type": "boolean"
+}
```

Changed2 schema fields changedv0.9.0Jul 3, 2026

changedInput schema / properties / lang / description

Previous value: -"Locale for formatting: en, es, pt, fr (other locales fall back to en)"New value: +"Locale for dates, provider attribution, and commentary: en, es, pt, fr (the summary scaffold stays English; other locales fall back to en)"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "date": {
+      "type": "string"
+    },
+    "degraded": {
+      "type": "boolean"
+    },
+    "informationalOnly": {
+      "type": "boolean"
+    },
+    "matchId": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "signal": {
+      "anyOf": [
+        {
+          "additionalProperties": true,
+          "properties": {},
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "signals": {
+      "items": {
+        "$ref": "#/properties/signal/anyOf/0"
+      },
+      "type": "array"
+    },
+    "team": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "informationalOnly"
+  ],
+  "type": "object"
+}

Changed1 schema field changedJun 12, 2026

changedInput schema / properties / team / description

Previous value: -"3-letter team code for that team's next fixture, e.g. MEX"New value: +"3-letter team code, e.g. MEX — resolves to the team's in-play match when one is live, else their next fixture"

First observedv0.1.0Jun 11, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations, it explains what the flagged states mean (complete:false = provider read incomplete, not absence of signal; partial = unusable fixture records), when the tool is unavailable, and constrains downstream use (relay factually, no betting/trading advice, no invented links). This is exactly the extra context annotations alone cannot carry.

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?

Selection modes are front-loaded in the opening sentence and every clause carries information (state flags, availability window, usage constraints). It is dense and runs long as one block, which slightly hurts scanability but not substance.

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?

With an output schema present, the description correctly avoids enumerating return fields yet still explains the two status flags an agent must interpret, plus availability and usage limits. Nothing needed to call or interpret it 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 adds real semantics: date defaults to today, matchId is the most specific selector, and team resolves to a live match or else the next fixture. It does not touch tz, lang, flavor, or competition resolution, so it stops short of a 5.

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 first sentence names a specific resource (prediction-market signals), its read-only nature, and the three selection axes (match id, team, date). It is clearly separable from siblings like get_match, get_today, or get_next_fixture, which return match/fixture data rather than market reads.

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 states the selection precedence ('by id', team resolving to in-play else next fixture, date defaulting to today) and a hard usage boundary: available only before and during a match, never for finished ones. It does not explicitly name a sibling tool to use instead for finished matches or non-market data, which keeps it from a 5.

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

Deploy Server

Prediction-market signal

Instructions

Input Schema

Output Schema

Schema Changelog

TDQS

Other Tools