Deterministic Music Theory for Claude, Cursor, and Autonomous AI Agents
Large Language Models (LLMs) frequently hallucinate music theory, leading to incorrect notes, false Roman numerals, and broken voice leading. THIRI solves this by providing a deterministic, mathematical music-theory engine (pitch-class-set theory over ℤ/12) directly to your AI.
It gives AI assistants precise, reproducible harmonic reasoning in milliseconds, allowing them to write correct musical scores, analyze progression
Parse a chord into root, quality, intervals, and (with a key) roman numeral + function.
| Name | Required | Description | Default |
|---|---|---|---|
| key | No | ||
| chord | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool as readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds the output components (root, quality, intervals) but does not disclose any additional behavioral traits such as error handling, edge cases, or format constraints. It adds some value but not rich context beyond 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that immediately states the action and outputs. It avoids redundancy and includes the key caveat about the key in a natural way. 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?
There is no output schema, so the description needs to explain return values; it does so by listing root, quality, intervals, and roman numeral + function. It also clarifies the role of the optional key. For a straightforward read-only analysis tool, this is sufficient, though it does not mention error behavior or chord notation specifics, keeping it just short of full completeness.
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. It does explain that 'key' is used to derive roman numeral and function (implying it is optional, as the schema does not require it), but it does not describe the expected format for the chord or key strings. This adds some meaning beyond the schema but leaves significant gaps.
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 'Parse' and a clear resource 'chord', and enumerates the outputs: root, quality, intervals, and roman numeral + function. This clearly distinguishes it from sibling tools like generate_voicing or reharmonize, which imply creation or alteration rather than analysis.
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 description implies usage for chord analysis and mentions that a key is needed for roman numeral/function, but it does not explicitly state when to use this tool versus alternatives or provide any exclusion criteria. It provides no direct comparison with siblings, so usage guidance is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Arrange a 4-piece band from a natural-language prompt. Returns conductor tempo/groove, 4 lanes of note events, lead sheet, and base64 MIDI. Audio render (Csound → WAV) stays on local thiri-conductor-mcp / POST /v2/render.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | ||
| durationSec | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it returns specific artifacts (tempo/groove, note lanes, lead sheet, base64 MIDI) and notes that audio rendering is deferred to an external endpoint, preventing misconceptions.
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?
Three purposeful sentences: purpose, output contents, and rendering behavior. Each sentence carries distinct information without redundancy or fluff, making it front-loaded and efficient.
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?
No output schema exists, but the description lists key return values adequately. However, it omits parameter details (durationSec) and any prompt constraints, leaving users guessing on important inputs for a complex generation tool.
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 0%, so the description must document parameters. It only implicitly covers 'prompt' via 'natural-language prompt'; 'durationSec' is entirely undocumented. This is a significant gap for schema-less 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 the tool arranges a 4-piece band from a natural-language prompt, using the specific verb 'arrange' and resource 'band.' This distinguishes it conceptually from sibling tools focused on chord analysis, voicing, reharmonization, or chord resolution.
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 description clearly signals use cases: when a full band arrangement from a natural-language prompt is needed. It does not explicitly name alternatives or exclusions, but the context is unambiguous compared to more granular sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Instrument-ready voicing in a style. Tension symbols voice by seat substitution (arranging practice, not stacking): 9/b9/#9 replace the root, #11/13/b13 replace the 5th, the 3rd and 7th are untouched guide tones. Pass voices: 5 to promote the implied 9 of an 11/13 chord; pass previousNotes for a voice-leading score.
| Name | Required | Description | Default |
|---|---|---|---|
| chord | Yes | ||
| style | No | ||
| octave | No | ||
| voices | No | ||
| keyContext | No | ||
| previousNotes | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It does disclose the key rule that tensions substitute for chord tones and explicitly warns against simple stacking ('arranging practice, not stacking'). However, it does not describe the output format, what 'instrument-ready' means concretely, or any notable limitations or side effects.
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 compact and information-dense, with no filler or repetition. It front-loads the primary purpose, then explains the substitution rules and the two most behavior-relevant parameters, so every sentence contributes meaningful operational 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?
Given six parameters, no output schema, and no annotations, the description is not complete enough for an agent to confidently invoke the tool. It omits the meaning of style, octave, and keyContext, does not state what the returned voicing looks like, and provides no guidance on when to prefer this tool over its siblings.
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?
All six parameters appear in the schema with type information, so schema coverage is high and the baseline is 3. The description adds semantic value for previousNotes and voices, but leaves style, octave, keyContext, and chord underspecified. It compensates only partially for the missing parameter descriptions.
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 identifies the tool's function as producing instrument-ready voicings in a given style, with a specific resource (chord symbols) and a concrete approach (seat substitution). It does not explicitly differentiate itself from sibling tools like analyze_chord or reharmonize, but the output and domain are clearly stated.
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 description gives useful parameter-level guidance ('pass voices: 5', 'pass previousNotes'), but it never states when to choose generate_voicing over the available alternatives. No exclusions or comparison against analyze_chord, conduct_band, or reharmonize are provided, leaving usage context largely implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Reharmonize a progression. Techniques: tritone_sub, ii_v_insertion, modal_interchange, diminished_passing, secondary_dominant, chain_of_dominants, coltrane_changes, backdoor (or auto).
| Name | Required | Description | Default |
|---|---|---|---|
| key | No | ||
| technique | No | ||
| progression | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds a list of techniques, which is useful, but it does not disclose behavioral traits beyond what annotations provide. Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description does not explain the return format, what 'auto' does, or how the transformation is applied.
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 concise: two sentences, front-loaded with the primary action, and uses a clear, enumerative list for techniques. No redundant or repetitive wording. Every sentence adds value.
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 has moderate complexity, and annotations cover safety, but there is no output schema. The description lacks details on return values, progression format, or the meaning of techniques like 'coltrane_changes'. It provides the essential purpose and options but is not comprehensive enough for correct invocation without additional context.
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?
With 0% schema description coverage, the description must compensate for parameter meaning. It explains the 'technique' parameter by listing valid values, and 'progression' is implied via the main action. However, the 'key' parameter is entirely undocumented, and the format of 'progression' (e.g., chord symbols) is not specified. Partial compensation but significant gaps remain.
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 the tool's purpose: 'Reharmonize a progression.' The verb 'reharmonize' is specific and the resource 'progression' is explicit. The list of techniques distinguishes it from sibling tools like analyze_chord or resolve_chord, making the tool's unique function clear.
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 description implies usage for reharmonizing chord progressions but does not explicitly state when to use this tool versus alternatives like analyze_chord or generate_voicing. It lists techniques but offers no guidance on choosing between them or when not to use the tool. Context is clear but exclusions and alternatives are missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Resolve a chord to spelled notes, frequencies, MIDI, and recommended scales.
| Name | Required | Description | Default |
|---|---|---|---|
| chord | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds the output categories (notes, frequencies, MIDI, scales) but no additional behavioral constraints or edge cases. No contradiction with annotations.
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 conveys the core action and outputs efficiently, and every word serves a 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?
The tool is simple (one parameter, read-only), and the description covers purpose and output categories. However, it omits input format and output structure, and there is no output schema to compensate. The missing chord-notation detail is a clear gap, making this minimally adequate.
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 input schema defines only a 'chord' string with no description or format. Schema description coverage is 0%, and the description merely says 'a chord' without specifying accepted notation (e.g., 'Cmaj7', 'C major', note list). This is a significant gap for correct invocation.
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 ('Resolve') with a clear resource ('a chord') and explicitly enumerates the outputs: spelled notes, frequencies, MIDI, and recommended scales. This distinguishes it from siblings like analyze_chord, generate_voicing, and reharmonize, which have different outputs/purposes.
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 description implies usage—use when you need chord resolution to notes/frequencies/scales—but provides no explicit guidance on when to prefer this tool over siblings or any exclusions. There is no mention of alternatives or prerequisites, so the guidance is only implicit.
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. Dates show when Glama detected each change.
generate_voicing1 field changedInput schema / properties / voicesAdded value: +{
+ "type": "number"
+}conduct_bandanalyze_chordgenerate_voicingreharmonizeresolve_chordClaiming 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 as io.github.acme/server also 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.json on 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.
No comments yet. Be the first to start the discussion!
Add one secure layer between your agents and this server.
analyze_chord, resolve_chord, and generate_voicing all operate on chord content and can easily be confused without reading the full descriptions. conduct_band is a clear outlier, while only reharmonize has a distinctly separate purpose.
Most tools follow a clean verb_noun snake_case pattern: analyze_chord, resolve_chord, generate_voicing, and conduct_band. reharmonize breaks the pattern by being a bare verb, but the naming style is otherwise predictable.
Five tools is a reasonable size for a focused server and avoids tool overload. However, conduct_band feels like it belongs in a separate arranging/conductor server rather than a chord intelligence server, which slightly weakens the set's focus.
The core chord-intelligence tasks are covered: analysis, resolution, voicing, and reharmonization. Missing obvious operations like chord inversion, transposition, or progression generation create noticeable gaps, and audio rendering is explicitly delegated elsewhere.