A
licenseA
qualityA
maintenanceDeterministic rails for game-running agents — verifies rule legality under SRD 5.2.1 via stateless, offline, sub-millisecond verdicts with citations.
24
2
MIT
Sports Rules
Server Details
Work an offside call through IFAB Law 11 or NHL Rule 83, step by step.
If you are the author of this connector, you can claim ownership with GitHub, an HTTP challenge, or a DNS record. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Available Tools
2 toolsoffsideWork an offside call through IFAB Law 11 or NHL Rule 83ARead-onlyInspect
Work an offside call through the published decision procedure — association football under IFAB Law 11, or ice hockey under NHL Rule 83 — and return every step, not just the verdict.
Use this for any "was that offside" question in either sport. The two rules are structurally OPPOSITE and are routinely conflated, and there are four specific things that get answered wrong:
SOCCER:
HANDS AND ARMS DO NOT COUNT, for anyone including goalkeepers. Only parts that could legally score are measured, and the boundary is the bottom of the armpit. This tool REFUSES to compute from an arm position rather than guessing where the shoulder was.
AN OFFSIDE POSITION IS NOT AN OFFENCE. It becomes one only with involvement in active play. Do not report "he was offside" when the answer is that he was in an offside position and uninvolved.
involvementis REQUIRED once the geometry makes it decisive — the tool errors rather than assuming, so ask the user what the player actually did, and pass "none" if the answer is nothing.No offside offence direct from a throw-in, goal kick, or corner. Absolute.
A DELIBERATE play by an opponent resets it; a deflection or a save does NOT. This is the distinction most arguments turn on.
HOCKEY: 5. SKATES decide it. Not the stick, not the body. 6. Since 2021 a skate in the AIR above the blue line is still onside — the line is a plane, and ice contact is irrelevant. BUT this does not apply to tagging up on a delayed offside, where the skate must contact the line. Do not generalise the 2021 change to tag-ups.
Input for soccer: positions along the attacking axis in metres, larger being nearer the opponents’ goal line — attacker, ball, secondLastDefender. Any consistent scale works; only the order matters. Optionally restart, foremostPart, inOwnHalf, involvement, lastTouch.
Input for hockey: rearSkate in centimetres relative to the LEADING EDGE of the blue line, negative being the neutral-zone side. Optionally skateOnIce, situation (zone-entry or tag-up), and stick.
Returns: a verdict of offside, onside, or no-offside-offence — three outcomes, not two, because "in an offside position but no offence" is a real and common answer — plus every step with the decisive one flagged, warnings, and a disclaimer.
THIS IS NOT AN OFFICIAL RULING. Relay the steps, not just the verdict: in a real call the procedure is the easy half and the inputs are the argument. Do not quote IFAB or NHL rule text; it is copyrighted and this tool does not reproduce it.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ball | No | SOCCER. Position of the ball, same scale. | |
| sport | Yes | Which rule book. The two are structurally opposite — do not mix them up. | |
| stick | No | HOCKEY. Ignored, and reported as ignored. Skates decide it. | |
| restart | No | SOCCER. There is NO offside offence direct from a throw-in, goal kick, or corner. Always ask which restart it was before answering. | |
| attacker | No | SOCCER. Position of the attacker along the attacking axis, larger being nearer the opponents’ goal line. Any consistent scale; only the order matters. | |
| inOwnHalf | No | SOCCER. A player in their own half cannot be in an offside position. | |
| lastTouch | No | SOCCER. A DELIBERATE play by an opponent resets offside. A deflection, a save, or a rebound off the frame does NOT. | |
| rearSkate | No | HOCKEY. The trailing skate in centimetres relative to the LEADING EDGE of the blue line — the edge nearer the attacking zone. Negative is the neutral-zone side; positive means it has broken the plane. | |
| situation | No | HOCKEY. zone-entry (default), or tag-up for clearing a delayed offside. The same skate position can give opposite answers. | |
| skateOnIce | No | HOCKEY. Since 2021 this does NOT affect a zone entry — a skate above the plane is onside. It is decisive when tagging up, where the skate must contact the line. | |
| involvement | No | SOCCER. REQUIRED once the player is in an offside position — the call errors without it rather than assuming. An offside POSITION is not an offence; this is what turns it into one, and "none" is a common and correct answer meaning play continues. | |
| foremostPart | No | SOCCER. Which part the attacker position describes. Passing an arm or hand is REFUSED with an explanation: only parts that could legally score count, and the boundary is the bottom of the armpit. | |
| secondLastDefender | No | SOCCER. Position of the SECOND-last opponent, same scale. Usually the last outfield defender, since the goalkeeper is normally the last. | |
| deliberatePlayCriteriaMet | No | SOCCER. Which of IFAB’s five deliberate-play criteria are met. Reported, not scored — there is no pass mark. |
TDQS
A4.6/5.0
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes well beyond the readOnlyHint/openWorldHint annotations by disclosing that the tool refuses arm/hand inputs, errors if involvement is missing, reports the hockey stick as ignored, returns three possible outcomes, and does not reproduce copyrighted rule text. It also explains that it is not an official ruling and flags the decisive step, all 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?
The description is long but appropriately structured for a two-sport, 14-parameter tool: a front-loaded purpose statement, sport-specific numbered warnings, and clearly separated input conventions. Each substantial block addresses a distinct failure mode or clarification, and there is little filler relative to the complexity being handled.
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 no output schema, the description properly specifies the return shape: a verdict of offside, onside, or no-offside-offence, every decision step, the flagged decisive step, warnings, and a disclaimer. It also covers required vs optional inputs, error behavior, and the copyright limitation on quoting rule text, making it complete enough to call the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Even though schema coverage is 100%, the description adds crucial semantics: any consistent scale works and only order matters for soccer positions, rearSkate is measured relative to the leading edge of the blue line with negative on the neutral-zone side, and involvement is required once geometry becomes decisive. It also clarifies that passing an arm/hand is refused, which is meaningful beyond the enum and field descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool works an offside call through IFAB Law 11 or NHL Rule 83 and returns every step, not just the verdict. It also says to use it for any 'was that offside' question in either sport. However, it never explicitly distinguishes itself from the sibling tool offside_rule_contrast, so differentiation is left to inference.
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?
"Use this for any 'was that offside' question in either sport" is an explicit when-to-use statement, and the warnings about asking for involvement and restart give clear operational guidance. However, it provides no when-not-to-use condition or mention of the sibling offside_rule_contrast as an alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
offside_rule_contrastHow soccer offside and hockey offside differARead-onlyInspect
Return the structural differences between soccer offside and hockey offside, dimension by dimension.
Use this when someone asks how the two compare, or when you are about to reason about one sport using an intuition from the other — which is the commonest way to get either wrong. They differ on what part of the player is measured, when the picture freezes, whether position alone is an offence, what happens at exactly level, what resets the situation, and which restarts are exempt.
Takes no arguments. Returns the comparison table.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
A4.5/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark it read-only and closed-world, and the description adds useful behavioral context by stating it returns a comparison table. Since there is no output schema, disclosing the return format and the dimensions covered gives the agent a clear picture of what to expect.
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?
Each sentence earns its place: purpose, usage context, the list of comparison dimensions, and the return format. It is compact, front-loaded, and free of filler.
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?
For a zero-argument comparison tool with no output schema, the description is complete: it gives the exact scope, the trigger conditions, the dimensions covered, and the return type. An agent can confidently select and invoke this tool without further clarification.
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?
The tool takes zero parameters, so the baseline is 4. The description additionally states 'Takes no arguments,' which removes any doubt even though the schema already makes this clear.
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 opens with a specific verb and resource: 'Return the structural differences between soccer offside and hockey offside, dimension by dimension.' This clearly identifies what the tool does and inherently distinguishes it from the single-sport sibling 'offside'.
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 explicitly states when to use the tool: when someone asks how the two compare, or when reasoning about one sport using intuition from the other. It does not name the alternative tool or explicitly state when not to use it, so it falls just short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
2 tool updates
- First observed
offside - First observed
offside_rule_contrast
Frequently Asked Questions
Claiming proves that you control a remote MCP connector. It does not move, proxy, or interrupt the server.
Open the connector listing, choose Claim ownership, and sign in to Glama.
Complete one verification method:
GitHub identity — fastest for official registry listings. For a namespace such as
io.github.alice/server, link the matching GitHub user, then choose Claim with GitHub. An organization namespace such asio.github.acme/serveralso needs that organization to have installed the Glama AI GitHub App and approved its permissions, because GitHub discloses organization membership only to apps it has installed. Use HTTP or DNS when it has not.HTTP challenge — works when you can deploy a public file. Generate a token, publish the exact JSON Glama shows at
/.well-known/glama.jsonon the same origin as the connector, then choose Check HTTP challenge.DNS challenge — works when you control DNS but cannot change the server. Generate a token, create the exact TXT record Glama shows, wait for it to propagate, then choose Check DNS challenge.
After verification, Glama sends a confirmation email and gives you access to listing details, thumbnails, health checks, and analytics. Keep the HTTP file or DNS record in place: Glama periodically checks it and ownership remains verified while the token is discoverable.
The HTTP ownership file has this structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"claim": "glama_claim_..."
}Claim tokens are opaque, stable, and bound to the signed-in Glama account. They contain no email address or other personal information. If Glama can no longer discover a verified HTTP or DNS token, it starts a seven-day grace period before removing claim-based access. Restore the same token during that period to keep ownership verified. Never publish an email address, Glama session token, GitHub token, or connector credential as ownership proof.
If verification fails, confirm that you copied the current token exactly. The HTTP file must be public, return valid JSON with a successful HTTP response, and stay on the connector's origin. DNS changes may need more time to propagate. A claim cannot transfer to a different origin or hostname: if the connector target changes, Glama starts the grace period and the new target must be claimed separately after the previous claim is released.
For a connector linked to the official MCP Registry, registry updates continue to replace its name, description, and URL by default. After claiming, open Manage connector and enable Use Glama listing details as the source of truth if edits made on Glama should be preserved. Categories and thumbnails are always managed on Glama; registry linkage and technical connection settings continue to sync.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
To improve your MCP server's ranking:
Claim ownership of the server listing
Complete the server profile with an accurate description and thumbnail
Provide a test profile so Glama can connect to and evaluate the server
Keep tool definitions clear and complete to earn a high Tool Definition Quality Score (TDQS)
Route real usage through the Glama Gateway; more recorded successful server uses also improve the ranking
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!
Related MCP Connectors
The Laws of the Game and world football's major competitions, every claim cited to primary sources
The deciding place: argue the call, decide, keep the reasons, get the work back as finished files.
Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
Related MCP Servers
- AlicenseAqualityAmaintenanceAuthor rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.8MIT
- AlicenseNot gradedqualityDmaintenanceEnables humanitarian negotiators to analyze complex situations using proven methodologies like Island of Agreement, Iceberg analysis, and stakeholder mapping. Provides structured frameworks for establishing common ground, understanding deeper motivations, and developing strategic engagement plans in high-stakes humanitarian contexts.MIT
- AlicenseBqualityBmaintenanceMCP server for refereeing tabletop RPG sessions by analyzing transcripts against a configurable charter, providing deterministic findings on rule violations like unanswered questions or unacknowledged dice rolls.2MIT
Try in Browser
Glama MCP Gateway
Add one secure layer between your agents and this server.
TDQS
A4.5/5.0
Disambiguation5/5
The offside tool computes a call for a specific scenario, while offside_rule_contrast returns a static comparison table. Their purposes are completely distinct and clearly labeled; no agent could confuse which to invoke.
Naming Consistency5/5
Both tools use lowercase snake_case and share the 'offside' domain prefix. While not verb_noun, the pattern is perfectly consistent given the server's narrow scope.
Tool Count3/5
At two tools, the server is minimal but tailored to a hyper-specific purpose (offside in soccer and hockey). It feels slightly thin—an 'explain offside rule' per sport might round it out—but the two tools cover the core use cases.
Completeness4/5
For the inferred domain of offside decisions across two sports, the tools cover the decision procedure, key edge cases, and cross-sport differences. A minor gap is the lack of a standalone rule explainer, and the server name 'Sports Rules' suggests a broader scope that isn't implemented.