Remote HTTP MCP that generates verified Next.js component scaffolds with integrity stamps for Claude/Cursor agents.
Syncs a project's local clone with its base branch (pulling if it has fallen behind), applies file changes on a new branch, validates the build when the repo is a Node project, and opens a Pull Request for human review. The agent never pushes to the base branch directly. Requires the BotKelp account key that registered the project — fails for a project id you don't own, the same as for an unknown one.
| Name | Required | Description | Default |
|---|---|---|---|
| files | Yes | ||
| prBody | Yes | ||
| prTitle | Yes | ||
| projectId | Yes | ||
| reviewers | No | ||
| botKelpKey | Yes | BotKelp account key (starts with "bk_live_"). Required. | |
| branchName | Yes | Name for the new branch, e.g. agent/add-supabase-auth | |
| githubToken | Yes | GitHub PAT with repo write access, used for the clone/push and the PR. | |
| commitMessage | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden. It discloses the full workflow, the constraint about never pushing to the base branch, and the ownership/auth requirement. It could further clarify failure behavior after build validation, but it is substantially transparent.
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 dense sentences convey the complete workflow, constraints, and auth requirement without repetition. The most important behavioral information is front-loaded, and every clause 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?
For a tool with 9 parameters, no output schema, and no annotations, the description covers the core workflow and constraints but omits details like what the tool returns, what happens on build failure, and how reviewers or other optional fields factor in. It is adequate but leaves meaningful 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%, and the description does not compensate for the remaining parameters. It adds useful ownership context for botKelpKey/projectId and implies roles for files, branchName, and PR fields, but it does not clarify exact formats, relationships, or required values for most 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 states a specific multi-step action: syncs the clone, applies changes on a new branch, validates the build, and opens a PR. It is clearly differentiated from the sibling scaffold/template tools, which operate on different resources entirely.
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 a clear context for use: applying file changes to a project and opening a PR for human review. It does not explicitly name an alternative tool to use instead, but no sibling tool competes for this job, so the guidance is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Same repo hand-off as get_scaffold_template — a private GitHub repo BotKelp owns and manages itself, plus a short-lived clone credential — but paid per call in USDC via the x402 protocol instead of a BotKelp account: no signup, no API key, callable by any agent with its own wallet. Call once without a payment to receive the price and payment requirements (HTTP 402-style, in the tool result's accepts field), then retry the same call with _meta["x402/payment"] set to a signed x402 payment matching those requirements. You are only charged if the call succeeds.
| Name | Required | Description | Default |
|---|---|---|---|
| components | Yes | Component ids to include, e.g. ["nextjs-base", "tailwind", "supabase-client"]. | |
| projectName | No | Name used in package.json and templates. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden, and it delivers: it discloses that the repo is private and BotKelp-managed, that credentials are short-lived, that payment is charged only on success, and that the first unpriced call returns an HTTP 402-style response. This goes well beyond a generic 'buy' statement.
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 dense but efficient, with each clause contributing to the payment workflow or the distinction from the sibling. It is somewhat long due to the x402 protocol complexity, but no sentence is wasted. Splitting the long first sentence could improve readability without changing substance.
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 payment-gated tool with no output schema, the description covers the critical behavior: how to obtain payment requirements, how to pay, and when charges occur. It does not describe the full return payload beyond the `accepts` field, but it provides enough for an agent to invoke the tool correctly and interpret the payment flow.
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 100%, so the schema already documents both parameters. The description adds no parameter-level detail beyond referencing `_meta["x402/payment"]`, which is not part of the input schema but is essential for the payment workflow. Baseline 3 is appropriate since the schema does the heavy lifting.
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 and resource: buying a scaffold template via paid hand-off. It explicitly contrasts with get_scaffold_template, clarifying that this variant is paid per call and available without a BotKelp account. An agent can distinguish this from its sibling without ambiguity.
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?
Provides explicit two-step usage: call without payment to receive price/requirements, then retry with a signed x402 payment in `_meta`. It also explains when this tool is appropriate compared to the account-based sibling, since it requires no signup or API key. This is strong, actionable guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read-only, side-effect-free: compares the component versions you currently have pinned against BotKelp's current registry and reports what has newer versions available, plus each component's latest CI freshness status. BotKelp never reads your repo itself — pass the versions you currently have. Call this on whatever schedule you like (daily, weekly, on demand); nothing is pushed or applied automatically. Requires an BotKelp account key with sufficient credit.
| Name | Required | Description | Default |
|---|---|---|---|
| botKelpKey | Yes | BotKelp account key (starts with "bk_live_"). Required. | |
| componentPins | Yes | The component ids and versions you currently have, read from your own local copy. |
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 clearly states read-only, side-effect-free behavior, that BotKelp never reads the repo, and that no automatic push/apply occurs. It also mentions the account key credit requirement. Minor gaps like rate limits or exact failure modes are not covered, but the core behavior is well disclosed.
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 sentences, front-loaded with the most important trait ('Read-only, side-effect-free'), and every sentence adds relevant information about behavior, scheduling, or requirements. No fluff or repetition.
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 no output schema and no annotations, the description is complete enough for an agent to call it correctly. It explains the purpose, the required input, the return concept, scheduling, and prerequisites such as the account key and credit.
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 100%, so baseline is 3. The description reinforces that componentPins should be the currently pinned versions and that the key must have sufficient credit, adding slight meaning beyond the schema. However, this added value is marginal and largely redundant with the schema 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 states a specific verb ('compares') and resource ('component versions you currently have pinned against BotKelp's current registry'), and specifies the output: newer versions and CI freshness status. It also distinguishes itself from sibling tools by explicitly labeling the operation as read-only and side-effect-free.
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 clear usage context: it can be called on any schedule, requires the user to pass versions, and notes that nothing is pushed or applied automatically, implying it is not the tool for applying changes. It does not explicitly name an alternative tool, but the exclusion is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Register a project: links a GitHub repo the agent will maintain a persistent, synced local clone for, so future tasks can branch off an up-to-date base without re-cloning. Requires a BotKelp account key — projects are private to the account that registers them.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| repoUrl | Yes | GitHub repo URL, e.g. https://github.com/owner/repo | |
| baseBranch | No | Defaults to "main". | |
| botKelpKey | Yes | BotKelp account key (starts with "bk_live_"). Required. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the disclosure burden and does it well: it reveals that a persistent local clone is maintained and synced, that projects are private to the registering account, and that a key is required. It does not cover failure modes or returned status, but no annotation context exists to lean on.
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?
Two focused sentences that front-load the purpose, then add the key prerequisite and privacy behavior. Every clause earns its place; no redundant restating of the name or title.
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 plus schema covers what the tool does, why it exists, the prerequisites, and the key persistence behavior. It lacks explicit return/result details and error conditions, and there is no output schema to fill that gap, but it is sufficient for an agent to select and invoke the tool correctly.
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 75%, so the schema already documents repoUrl, baseBranch, and botKelpKey; the description adds the account key requirement and privacy nuance but nothing about the remaining name parameter. This is a reasonable middle score rather than a penalty for missing low-coverage compensation.
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 starts with a specific verb and resource ("Register a project") and explains the concrete effect: linking a GitHub repo and maintaining a persistent, synced local clone. This clearly distinguishes it from siblings like list_projects and apply_changes_to_repo.
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 gives a clear use context: register when future tasks should branch off an up-to-date base without re-cloning, and states the prerequisite BotKelp account key. It does not explicitly name alternatives or state when not to use it, which keeps this 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.
Generate a Next.js + Supabase + Tailwind project scaffold from the given component ids. Component requires are resolved automatically. Returns the full generated file tree as text so the calling agent can write the files itself. Omit apiKey for Local Mode: free, unauthenticated, files-only generation (no job tracking). Pass apiKey (a premium BotKelp key) to additionally record the attempt as a job. To get a private repo BotKelp manages itself instead of inline files, use get_scaffold_template.
| Name | Required | Description | Default |
|---|---|---|---|
| apiKey | No | BotKelp API key (starts with "bk_live_"). Omit for Local Mode — free, unauthenticated, files-only generation. | |
| components | Yes | Component ids to include, e.g. ["nextjs-base", "tailwind", "supabase-client"]. | |
| projectName | No | Name used in package.json and templates. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral disclosure burden. It goes beyond a simple 'generates a scaffold' statement by revealing that component requires are resolved automatically, that the return value is a file tree the agent must write itself, and that passing apiKey triggers job recording. This is strong context, though it does not mention potential side effects beyond job recording or any error/rate-limit 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?
The description is four sentences, each earning its place: primary action, automatic dependency resolution, return format, and mode/alternative guidance. The most important scoping information is front-loaded, and there is no redundant or filler content.
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 there is no output schema, the description explicitly states the return format (full generated file tree as text) and what the agent should do with it. It also covers both operational modes, the authentication implication of apiKey, and the relevant alternative. This is complete for an agent deciding whether and how to invoke the 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 description coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining the behavioral significance of apiKey (Local Mode vs. job tracking) and reinforcing that components are resolved recursively. This extra context justifies a score above baseline.
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 verb and resource: 'Generate a Next.js + Supabase + Tailwind project scaffold from the given component ids.' It also clarifies the distinct output format (full file tree as text) and differentiates itself from get_scaffold_template, which provides a privately managed repo instead of inline files.
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 explicitly explains when to omit apiKey (Local Mode) versus when to pass it (to record the attempt as a job), and it names get_scaffold_template as the alternative for a privately managed repo. This gives clear selection criteria relative to at least one key sibling tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Requests a build for the given component ids, backed by a private GitHub repo BotKelp owns and manages itself under its own org — never your account. Returns the repo's location and a short-lived, single-repo-scoped clone credential; clone it yourself, BotKelp never touches wherever you copy it to. Repeat requests for the same component combination reuse the same repo at no extra GitHub-side cost. Requires an BotKelp account key with sufficient credit — there is no free/local mode for this tool (see generate_scaffold for that). See check_component_updates to find out when a newer combination is available.
| Name | Required | Description | Default |
|---|---|---|---|
| botKelpKey | Yes | BotKelp account key (starts with "bk_live_"). Required. | |
| components | Yes | Component ids to include, e.g. ["nextjs-base", "tailwind", "supabase-client"]. | |
| projectName | No | Name used in package.json and templates. |
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 covers ownership (BotKelp's repo, never the user's account), return value (repo location + short-lived single-repo-scoped credential), side effects (clone it yourself, BotKelp never touches the copy), cost implications (no extra GitHub-side cost for repeats), and auth/credit requirements. This is comprehensive behavior disclosure.
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?
Four sentences each earn their place: purpose, return credential and scope, reuse behavior, and critical usage exclusions. The main verb and resource are front-loaded in the first sentence, and there is no filler or repetition.
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 tool with 3 parameters and no output schema, the description covers purpose, return value semantics, credentials, cost model, alternatives, and update checking. Nothing essential for correct invocation is missing.
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 100%, so the baseline is 3. The description adds meaningful context beyond the schema, notably the credit requirement for botKelpKey and the concept of a 'component combination' that makes the array semantics more concrete. projectName is not elaborated on, but the schema already explains it clearly.
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 verb ('Requests a build') and a specific resource (component ids backed by a private GitHub repo), and clearly differentiates this tool from generate_scaffold by cost model and from check_component_updates by purpose. An agent can understand exactly what the tool does and how it differs from siblings.
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 explicitly tells when NOT to use this tool ('there is no free/local mode for this tool (see generate_scaffold for that)') and points to check_component_updates for timing decisions. It also clarifies repeat requests reuse the same repo, giving the agent a clear decision rule for repeated use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the projects registered by this BotKelp account. Requires a BotKelp account key — never returns another account's projects.
| Name | Required | Description | Default |
|---|---|---|---|
| botKelpKey | Yes | BotKelp account key (starts with "bk_live_"). Required. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does add meaningful behavioral context: authentication is required and the tool deliberately scopes results to the BotKelp account, never returning another account's projects. This goes beyond what the name alone conveys.
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?
Two short, information-dense sentences. The core action is front-loaded, and the auth/privacy caveat follows naturally without padding.
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 read-only list tool with one parameter and no output schema, the description provides the essential context: what is listed, under what auth, and the privacy boundary. It does not detail response shape, but that gap is minor given the simplicity of the operation.
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 100% and the single parameter already documents its required status and prefix format. The description simply reuses the same concept without adding much new parameter-level detail, so baseline 3 is appropriate.
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 verb ('List') and resource ('projects registered by this BotKelp account'), clearly distinguishing this from siblings like create_project or generate_scaffold. It immediately identifies the scope of the list operation.
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 clear context: the tool lists the caller's own projects and requires an account key. However, it does not explicitly mention when to prefer this over alternatives or any exclusions, leaving usage guidance mostly implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the BotKelp component registry (Next.js/Supabase/Tailwind "Lego blocks"). Returns id, name, version, description, requires, conflictsWith, provides (capability tags, e.g. "authentication"), dependencies, envVariables, sources (docs/github-releases/github-examples citations proving this component was checked against real, current official material — not written from memory), and a freshness field (status/checkedAt/outdatedDependencies from the latest automated build check, or null if never validated) for each match — check freshness before relying on a component. Filter by free-text query and/or by provides capability tags (e.g. ["authentication"]) to discover components by what they do rather than needing to already know their ids. Call with no arguments to list everything.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Free-text filter matched against component id, name, and description. | |
| provides | No | Only return components whose `provides` includes every tag listed here, e.g. ["authentication"] or ["billing", "subscription-management"]. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does substantial work: it enumerates all returned fields, explains the freshness field's null/status semantics, clarifies that sources prove the component was checked against real material, and notes the no-arguments list-everything behavior. It does not explicitly say the operation is read-only, but 'search' plus the absence of side-effect language makes that reasonably implicit.
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 long but information-dense. Every clause earns its place: return-field detail, freshness caveat, filter modes, and the no-args behavior. There is mild redundancy in phrases like 'for each match' and the very elaborate definition of sources, but no filler. The main purpose is front-loaded.
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?
Since there is no output schema, the description compensates by listing all return fields and their semantics, including freshness and sources. With only two optional parameters fully documented in the schema, the description is sufficient for an agent to call the tool correctly. Minor omissions like pagination or ordering are not critical for this discovery/search 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 description coverage is 100%, so the baseline is 3. The description adds value beyond the schema by explaining the intent of the provides parameter — discovering components by what they do rather than knowing ids — and by documenting the behavior of calling with no arguments. These additions exceed the schema's literal property 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 starts with a specific verb and resource — 'Search the BotKelp component registry' — reinforced by the stack context 'Next.js/Supabase/Tailwind Lego blocks'. It clearly differentiates from the action-oriented siblings (create_project, apply_changes_to_repo, generate_scaffold) by framing itself as a discovery tool.
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 clear usage context: filter by free-text or provides capability tags to discover components by what they do, and call with no arguments to list everything. It also warns to check freshness before relying on a component. However, it does not explicitly name alternative tools or describe when not to use this tool, so it stops 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.
Runs a real npm install && npm run build against the given files and reports whether the project builds. Free, no API key needed. Use it after editing a generate_scaffold result (e.g. wiring a component into a page) before handing the project to the user. The build runs asynchronously: call once with files (the full project — every file, not just the ones you changed) and you get back status "WAIT" and a jobId; call again with that jobId until you get "OK" (it builds) or "FAIL" (it does not, with the compiler error). A build usually takes one to two minutes.
| Name | Required | Description | Default |
|---|---|---|---|
| files | No | The full project to verify — generate_scaffold's `files` output with your edits applied. Provide this to start a verification. | |
| jobId | No | A job id from a previous WAIT response. Provide this to check a verification already started. | |
| envVariables | No | Env var names to write placeholder values for before building (typically generate_scaffold's `envVariables` output) — needed for components that read process.env at build time (e.g. a Supabase client). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full behavioral burden and delivers: the async two-phase protocol (start with files → WAIT + jobId → poll with jobId → OK/FAIL with compiler error), the 'real' build side effect, the full-project requirement, cost ('Free, no API key needed'), and expected latency ('one to two minutes'). This is exactly the kind of behavior an agent cannot infer from the schema.
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?
Roughly 130 words covering purpose, cost, usage timing, the async handshake, failure output, and latency — every sentence earns its place. The core action is front-loaded and the complex two-phase protocol is explained in a single flowing passage without redundancy.
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 3-parameter async tool with no output schema and no annotations, the description covers the essential contract: start/poll invocation pattern, status values (WAIT/OK/FAIL), and failure detail. Minor gaps remain — the full response shape beyond status is unspecified and jobId's validity/error behavior is not addressed — but the core calling protocol is 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 100%, so the baseline is 3; the description adds real value on top by explaining the lifecycle connecting the parameters: files must be the entire project including edits, jobId originates from a prior WAIT response and drives polling, and envVariables maps to generate_scaffold's output. This goes beyond the schema's per-parameter text.
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-plus-resource statement: 'Runs a real `npm install && npm run build` against the given files and reports whether the project builds.' This clearly distinguishes verify_scaffold from its siblings, especially generate_scaffold, and explicitly anchors it in the generation workflow.
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 explicit workflow context: 'Use it after editing a `generate_scaffold` result... before handing the project to the user.' This tells an agent exactly when the tool applies. It stops short of naming when-not-to-use it or contrasting it with a sibling like check_component_updates, so it does not fully earn a 5.
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.
apply_changes_to_repobuy_scaffold_templatecheck_component_updatescreate_projectgenerate_scaffoldget_scaffold_templatelist_projectssearch_componentsverify_scaffoldClaiming 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.
Ohh nice feature to have
Add one secure layer between your agents and this server.
The nine tools split into clear functional clusters: registry discovery/update checks, project/repo management, and scaffold generation/delivery/verification. The three scaffold-delivery tools (generate_scaffold, get_scaffold_template, buy_scaffold_template) share a similar purpose, but their descriptions clearly separate inline files, account-backed private repos, and paid wallet-based access.
All tool names follow the same verb_noun snake_case pattern: apply_changes_to_repo, check_component_updates, create_project, generate_scaffold, get_scaffold_template, and so on. There are no camelCase or vague imperative names, so an agent can predict the action-object relationship across the whole server.
Nine tools is well within the ideal range, and each tool addresses a distinct part of the workflow: discovering components, generating and verifying scaffolds, obtaining managed templates, and managing linked repositories. No tool feels redundant or so out of place that the count becomes inappropriate.
The core workflow is covered: search components, check updates, generate and verify scaffolds, request a managed template, and apply changes to a linked repo via pull request. Minor lifecycle gaps remain, such as no way to delete or update a registered project, but agents can complete the main intended tasks.