Free public MCP server that analyzes football matches and returns explainable win, draw, and loss probabilities based on recent form, team performance, ratings, and match data.
Scored across 6 tools
Most tools have clearly distinct purposes: prediction, analysis, ranking, and data retrieval are separated well. The only mild overlap is between find_strongest_predictions and predict_matches, both operating over multiple matches, but their outputs differ enough to avoid real confusion.
All tool names follow a consistent snake_case verb_noun pattern, with verbs like get, predict, analyze, and find clearly indicating the action. The singular/plural predict_match versus predict_matches pair is intentional and readable.
Six tools is a well-scoped set for a sports prediction server. Each tool covers a distinct need: match discovery, team form, single prediction, batch prediction, evidence explanation, and ranking.
The tool surface covers the full prediction workflow: fetch upcoming matches, evaluate team form, predict individual matches, predict all matches, analyze evidence, and highlight strongest predictions. No critical gaps are apparent for the stated domain.
Return the evidence and team statistics used by the prediction model, without a prediction.
| Name | Required | Description | Default |
|---|---|---|---|
| away_team | Yes | ||
| home_team | Yes | ||
| competition | No | Optional free-tier competition name or code; improves team resolution |
| Name | Required | Description |
|---|---|---|
| data | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry behavioral disclosure. It does reveal a key trait: the tool returns evidence/stats and deliberately omits a prediction. However, it does not mention whether any side effects occur, whether team resolution may fail, or how the evidence is presented beyond what the output schema already covers. Minimal but not misleading.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with zero filler. It states the core action, the object, and the key exclusion ('without a prediction') clearly. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the basic purpose and a key exclusion, and the output schema likely covers return structure. However, it does not address how to specify teams (aliases, required format), when competition should be provided, or how this tool relates to get_team_form for team statistics. For a tool with no annotations, the description leaves several contextual gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 33%, with only 'competition' documented. The tool description does not clarify home_team and away_team formats, how teams are resolved, or what 'evidence' means in relation to these parameters. The description adds no semantic value beyond the schema, and the schema itself is thin for the two required parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('Return') and resource ('the evidence and team statistics used by the prediction model'), and explicitly clarifies what it does NOT do ('without a prediction'). This clearly distinguishes it from predict_match and predict_matches, which produce predictions, and orients the agent to the tool's analytical role.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'without a prediction' gives clear context for when this tool is appropriate: when the agent needs the model's underlying evidence and stats, not a forecast. It does not explicitly name sibling alternatives or state when not to use it, but the contrast with prediction-generating siblings is strong enough to guide selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Rank matches where the model has its clearest statistical preference.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | UTC date in YYYY-MM-DD format | |
| competition | Yes | ||
| minimum_confidence | No | Medium |
| Name | Required | Description |
|---|---|---|
| data | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that the tool ranks matches by model preference, but it does not explain whether predictions are newly computed, which confidence threshold applies, or how ranking is ordered or limited.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single front-loaded sentence with no filler words. It is efficient, though somewhat terse; it earns its place but leaves room for more useful detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The output schema mitigates return-value ambiguity, but the description still omits parameter semantics and alternative-selection guidance. For a tool placed among prediction-related siblings, the agent lacks enough context to confidently choose it over similar tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 33%, and the tool description does not compensate. The meaning of competition and minimum_confidence is left to inference, and there is no explanation of how minimum_confidence maps to 'clearest statistical preference'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action ('Rank'), a resource ('matches'), and a clear criterion ('clearest statistical preference'). It does not explicitly distinguish itself from sibling predict_matches, but the emphasis on ranking by model preference gives it a distinct purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given about when to use this tool instead of siblings like predict_matches or predict_match. There are no exclusions, alternatives, or contextual conditions, so the agent must infer usage from the name and general phrasing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Calculate recent results, goals, and a normalized form score for a team.
| Name | Required | Description | Default |
|---|---|---|---|
| team | Yes | ||
| competition | No | ||
| number_of_matches | No |
| Name | Required | Description |
|---|---|---|
| data | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It conveys that this is a read-only calculation with no apparent side effects, but it does not explain how 'recent' is defined, how the normalized form score is computed, or any data-source behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence with no filler or redundancy. The core action and target are immediately clear, and every word contributes to the purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Although an output schema exists, the description omits usage guidance and leaves two of three parameters unexplained. For a tool with no annotations and zero schema description coverage, this is too thin for an agent to confidently call it with the right optional arguments.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate for parameter meaning. It clarifies that the 'team' parameter refers to the team whose form is being calculated, but it provides no meaning or context for the optional 'competition' or 'number_of_matches' parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific verb ('Calculate') and resource (team form), and lists the outputs: recent results, goals, and a normalized form score. It is distinct from the sibling prediction/analysis tools, though it does not explicitly name or differentiate itself from them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance about when to use this tool versus alternatives such as analyze_match or predict_match. No prerequisites or exclusions are provided; the usage context is only implied by the tool's purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get upcoming football matches for a free-tier competition and UTC date.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | UTC date in YYYY-MM-DD format | |
| competition | Yes |
| Name | Required | Description |
|---|---|---|
| data | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden itself. 'Get' implies a read-only operation, and 'upcoming' plus 'free-tier competition' communicates filtering behavior. However, it does not disclose edge-case behavior such as what happens for unsupported competitions, invalid dates, or whether the date is an exact day or a range starting point.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no filler. Every phrase adds information: the action, the resource, the competition constraint, and the time zone.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is relatively simple and an output schema exists, so return values do not need to be described. Still, the description leaves ambiguity about how the date and 'upcoming' interact, and it offers no alternative routing or usage context, making it adequate but not fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 50% because the competition parameter lacks a description. The description partially compensates by mentioning competition and UTC date, and by adding the 'free-tier' qualifier, but it does not explain competition value semantics or the exact meaning of the date in relation to 'upcoming' beyond what the schema already says.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Get') and resource ('upcoming football matches') and adds useful constraints ('free-tier competition', 'UTC date'). It is clear enough to distinguish from siblings like predict_match or get_team_form, though it does not explicitly contrast itself with them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus alternatives such as predict_matches or find_strongest_predictions. The description implies a basic use case but provides no exclusions, comparisons, or context for selecting it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Estimate home, draw, and away probabilities and explain the main statistical factors.
| Name | Required | Description | Default |
|---|---|---|---|
| away_team | Yes | ||
| home_team | Yes | ||
| competition | No | Optional free-tier competition name or code; improves team resolution |
| Name | Required | Description |
|---|---|---|
| data | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure, and it does communicate that the tool outputs probabilities and an explanatory narrative. However, it omits data dependencies, caveats about prediction reliability, and what happens when input teams are unrecognized or data is sparse.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one tight, front-loaded sentence with no filler. It earns its place, though the brevity sacrifices usage guidance and behavioral caveats.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a three-parameter tool with an output schema, the core invocation is minimally covered. However, the description does not help an agent choose between this and predict_matches, and it lacks edge-case or failure-mode context, making it only adequately complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 33%, and the description adds no parameter-level meaning beyond the self-evident names home_team and away_team. It also never mentions the optional competition parameter or clarifies whether team names must be full names, abbreviations, or IDs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a concrete deliverable: home/draw/away probabilities plus an explanation of statistical factors. It is clear about the outcome but does not distinguish itself from siblings like predict_matches or analyze_match, so it falls short of a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus predict_matches, analyze_match, or get_team_form. There are no when-not-to-use conditions or alternative referrals; the only usage signal is implied by the verb 'estimate'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Predict every scheduled match in a competition on a UTC date using one shared evidence set.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | UTC date in YYYY-MM-DD format | |
| competition | Yes |
| Name | Required | Description |
|---|---|---|
| data | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full behavioral burden. It discloses a notable trait beyond the schema: all predictions in the batch use 'one shared evidence set,' which is important for understanding result consistency. It does not explicitly state side effects or permissions, but 'predict' plus the presence of an output schema makes pure computation the natural reading.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence front-loads the action and scope and adds one meaningful behavioral clause ('using one shared evidence set'). There is no filler or repetition of schema details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter tool with an output schema, the core task and inputs are fully specified. The main remaining gaps—sibling selection and preconditions—are largely addressed by the batch wording and by the output schema, so nothing essential is missing for a correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description mentions both required parameters ('competition' and 'UTC date'), and the schema already describes the date format. With competition lacking a schema description, the description only repeats the term rather than explaining valid values or formats, so it partially compensates but adds little beyond naming.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource ('Predict every scheduled match in a competition on a UTC date'), immediately distinguishing it from the singular sibling predict_match and the retrieval-focused siblings. It states exactly what the tool produces and for which scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It clearly implies the batch scenario: use this when you want predictions for all scheduled matches in a competition on a given UTC date. It does not explicitly name alternatives or exclusions, but the 'every scheduled match' phrasing separates it from single-match prediction without needing further explanation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
analyze_matchfind_strongest_predictionsget_team_formget_upcoming_matchespredict_matchpredict_matches
Add one secure layer between your agents and this server.