Provides tools for listing Pages projects and deploying to a Pages project (with dry-run default and fixed project list).
Provides tools for checking account status, listing invoices, and sending invoices (with dry-run default).
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@allternit-ops Search brain for notes on the new client onboarding"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Single MCP gateway for Allternit LLC business operations. Stdio MCP server — every business-ops skill, delegated CLI agent (kimi/codex/agy), and future autonomous agent should go through this instead of touching Stripe keys, wrangler, or the brain directly.
Tool | Effect | Safety |
| Read-only account status check | none needed |
| Read-only invoice list | none needed |
| Wraps | defaults to |
| Read-only | none needed |
| Deploys a directory to a Pages project | prints the command only unless |
| Grep over | read-only |
| Read one brain doc | read-only, path-traversal-guarded to the brain root |
| Look up which model tier/backend to use for a task class ( | read-only; only meaningful when spawning a subagent or autonomous agent — an interactive session stays on its own model |
| Creates | local file writes only — never touches Stripe or sends anything; those steps stay manual per the playbook |
Related MCP server: Corben MCP Server
cd ~/Desktop/Allternit/allternit-ops
npm installRequires: python3 (for stripe_send_invoice), the Stripe key in the macOS Keychain (security find-generic-password -s stripe-allternit -w, fallback env var STRIPE_KEY), and network access to api.stripe.com. Cloudflare tools shell out to npx wrangler, which resolves an already-OAuth-authed wrangler — no separate credential needed on this Mac.
Add to Claude Code's MCP config (claude mcp add or the relevant .mcp.json/settings entry):
{
"mcpServers": {
"allternit-ops": {
"command": "node",
"args": ["/Users/joe/Desktop/Allternit/allternit-ops/index.js"]
}
}
}stripe_charges_enabled fails with a permission error on the current claude-setup restricted key — it lacks the accounts_kyc_basic_read scope needed for GET /v1/account. Add that scope via the Stripe dashboard (link is in the error message) if this tool needs to work; everything else (invoices, customers) already has write access per allternit-brain/infra/stripe.md.
Money- and deploy-affecting tools mirror send_invoice.py's own --dry-run-by-default pattern: nothing irreversible happens without an explicit confirm: true.
cloudflare_deploy_pages only accepts project names from a fixed list (sourced from allternit-brain/infra/cloudflare.md) so a typo can't push to the wrong project.
This is intentionally a separate package from the platform's own mcp/servers (which turned out to be an unrelated MCP-Apps/interactive-capsules protocol library, not a tool-server scaffold) — company-ops tooling stays out of the product repo.
Read a specific allternit-brain doc by path relative to the brain root (e.g. "company/offer.md").
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Path relative to allternit-brain/, e.g. "company/offer.md". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It indicates a read operation (non-destructive) but does not mention error handling, output format, or limits. Adequate for a simple read.
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 that is front-loaded with the action and includes a concrete example. No unnecessary words.
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 the simplicity of the tool (one parameter, no output schema, no nested objects), the description is sufficient. It doesn't explain the return value but that is typically implied for a read 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?
The input schema covers 100% of the single parameter with a description. The tool's description adds an example and clarifies the path is relative to the brain root, providing additional meaning beyond the schema.
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 'Read a specific allternit-brain doc' with a verb and resource, and provides an example path. It implicitly distinguishes from the sibling 'brain_search' which is for searching.
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 tells how to use the tool (by path relative to brain root) but does not explicitly state when to use it versus alternatives like brain_search. Usage is implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search allternit-brain markdown docs for a text query (case-insensitive substring match). Returns matching file paths, line numbers, and lines.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Text to search for. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility. It discloses the search method (case-insensitive substring match) and the return format (file paths, line numbers, lines). However, it does not explicitly state that it is read-only, though it is implied.
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 sentence that efficiently conveys purpose, method, and return structure with no wasted words.
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 the low complexity (one parameter, no nested objects, no output schema), the description is fairly complete. It specifies the return structure despite missing output schema. However, it could better contextualize usage relative to 'brain_read'.
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 schema already describes 'query' as 'Text to search for.' The description adds that it is a 'text query' and specifies the match is case-insensitive substring, enhancing the schema's meaning.
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 ('Search') and resource ('allternit-brain markdown docs'), and further clarifies the search method as 'case-insensitive substring match'. This clearly distinguishes it from sibling tool 'brain_read'.
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 use for text search but does not explicitly state when to use this tool versus alternatives like 'brain_read'. No when-not or alternative guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a new client folder under Allternit LLC/06_Client_Ops_and_Contracts// and copy in the standard business-ops-kit templates (MSA, SOW, Intake, NDA, Change Order, Support/SLA), named per the kickoff playbook convention. Does not create Stripe customers or send anything — those steps stay manual per the playbook.
| Name | Required | Description | Default |
|---|---|---|---|
| client_name | Yes | Client folder name, e.g. "Acme_Corp" (use underscores, matching the Swyft_Market convention). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It clearly states the folder creation, template copying, naming convention, and explicitly what it does not do (no Stripe customers, no sending). This provides comprehensive behavioral insight.
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 two sentences, front-loaded with the action and path, and no wasted words. Every sentence adds critical context.
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 single-parameter tool with no output schema and unrelated siblings, the description fully explains the tool's purpose, behavior, and constraints. It is complete and self-contained.
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 3. The description adds value by detailing the naming convention (underscores, Swyft_Market convention) and the folder path, which goes beyond the schema's description.
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 explicitly states the action (create folder), the specific path under Allternit LLC, and the templates copied. It distinguishes itself by clarifying what the tool does NOT do (Stripe/sending), setting it apart from any related tools.
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 folder setup and notes that other steps remain manual, but it does not explicitly state when to use this tool versus alternatives or provide exclusion criteria. The sibling tools are unrelated, so no direct comparison.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Deploy a directory to a known Cloudflare Pages project. Without confirm:true, only prints the command that would run — does not deploy.
| Name | Required | Description | Default |
|---|---|---|---|
| confirm | No | Set true to actually run the deploy. Omit or false to preview the command only. | |
| project | Yes | Target Pages project name — must be one of the known projects. | |
| directory | Yes | Directory to deploy, relative to the Allternit-websites repo root (e.g. "projects/services.allternit.com/source"). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full burden. It explicitly discloses the dry-run behavior when confirm is false, a key safety mechanism. No side effects or prerequisites are mentioned, but the disclosure is sufficient for understanding the tool's safe preview mode.
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 concise sentences: first states purpose, second adds critical usage condition (confirm flag). No waste, front-loaded, and easy to parse.
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?
With 3 parameters (all described), no output schema, and no complex nested objects, the description is nearly complete. It could mention what the tool returns (e.g., command text or deploy result), but the core behavior is well-covered.
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 baseline is 3. The description reinforces the confirm parameter's semantics ('does not deploy' when false), but adds minimal new information beyond the schema. The enum for project is clear from the schema.
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 deploys a directory to a known Cloudflare Pages project. It specifies the verb 'deploy' and resource, and distinguishes from sibling tools like cloudflare_list_pages_projects by focusing on deployment.
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 explains the confirm parameter's critical role (preview vs. actual deploy). It implies the project must already exist (known project). While it doesn't explicitly compare to alternatives, siblings are mostly unrelated, so context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List Cloudflare Pages projects via wrangler (read-only).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the tool is read-only, which is a key behavioral trait. However, it does not mention rate limits, authentication requirements, or what happens if no projects exist (e.g., empty list vs. error). More transparency would be beneficial.
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 sentence that is front-loaded with the core action and resource. It contains no unnecessary words and every part contributes to understanding.
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 no output schema, the description does not explain what the tool returns (e.g., list of project names, full details, or status). It also does not mention pagination or filtering. While adequate for a simple list tool, it lacks clarity on the output format.
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 has no parameters, so the description adds value by specifying the tool is 'via wrangler' and 'read-only', which are not captured in the schema. This provides context beyond the empty schema. Baseline is 4 due to zero 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 uses the specific verb 'List' and identifies the resource as 'Cloudflare Pages projects', distinguishing it from sibling tools like deploy or search. The method 'via wrangler (read-only)' adds specificity, making the purpose clear and unambiguous.
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 explicit guidance on when to use this tool versus alternatives. The read-only nature implies it's for listing without side effects, but no exclusions or prerequisite conditions are provided. Usage is implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up which model tier/backend to use for a task class, per model-routing.json (Allternit's A:// tier policy). Only meaningful when explicitly spawning a subagent or an autonomous agent — an already-running interactive session stays on its own model.
| Name | Required | Description | Default |
|---|---|---|---|
| task_class | No | One of: classification, draft_generation, client_coding_work, quote_routine, architecture_or_novel_judgment, quote_tier_c_scoping, creative_or_long_form, guardrail_check. Omit to list all task classes. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, but the description indicates a read-only lookup operation. It does not mention side effects or edge cases, but for a simple lookup, it is sufficiently 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?
Two sentences, no wasted words. Purpose is front-loaded. Each 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?
Given no output schema, the description does not specify return values. However, for a simple lookup, the agent can infer a model tier string. It is mostly 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 100%, so baseline is 3. The description adds 'per model-routing.json (Allternit's A:// tier policy)' but does not significantly enhance the parameter meaning beyond the schema's own description.
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 verb 'look up' and the resource 'model tier/backend for a task class' with reference to a specific policy file. It is distinct from sibling tools which are unrelated (Stripe, Cloudflare, brain).
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 states when the tool is meaningful (spawning subagents/autonomous agents) and when it is not (interactive sessions). This provides clear usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check whether the Allternit Stripe account can currently accept charges (read-only). Returns charges_enabled and any pending verification requirements.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description bears full burden. It explicitly states 'read-only', return values, and pending requirements. Lacks info on rate limits or side effects, but for a check operation it's sufficient.
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 sentences, front-loaded with action and return info, no unnecessary words. Highly 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, so description must cover return values. It does so but lacks data types or structure. Adequate for a simple zero-param 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?
No parameters, so schema coverage is 100%. Description adds value by naming return fields (charges_enabled, verification requirements), exceeding the baseline of 4 for zero params.
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?
Clearly states action ('Check whether the Allternit Stripe account can currently accept charges'), is read-only, and specifies return fields. Distinguishes from siblings like stripe_list_recent_invoices or stripe_send_invoice.
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 explicit when/when-not usage or alternatives are given. The read-only nature implies use before initiating charges, but guidance is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List recent Stripe invoices (read-only).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max invoices to return (default 10). | |
| customer | No | Filter to a specific Stripe customer id (e.g. cus_...). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only indicates 'read-only', which implies non-destructiveness, but does not describe rate limits, pagination behavior, default ordering, or any other operational characteristics that would help an agent understand side effects or constraints.
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, efficient sentence with no redundant language. It is appropriately sized for a simple list tool, though it could be slightly more structured with a separate line for parameters or usage tips.
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 the lack of output schema, the description should explain the response format (e.g., list of invoice objects). It does not mention return fields, pagination, or how 'recent' is defined. For a list tool with optional filters, this omission limits 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?
The input schema has 100% description coverage, with both parameters (limit, customer) already documented. The tool description adds no additional meaning or context beyond what the schema provides, so baseline score of 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 clearly states 'List recent Stripe invoices (read-only).' It specifies the verb 'list', the resource 'recent Stripe invoices', and indicates read-only behavior, which distinguishes it from sibling tools like stripe_send_invoice (send) and stripe_charges_enabled (check charges).
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 provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or when not to use it, leaving the agent to infer usage context from the tool name and siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Draft (and optionally send) a Stripe invoice by wrapping send_invoice.py. Defaults to a dry run that creates the draft and prints totals without sending — pass confirm:true to actually finalize and send.
| Name | Required | Description | Default |
|---|---|---|---|
| sow | No | SOW reference for the invoice memo (default SOW-2026-001). | |
| rate | No | Hourly rate in dollars (default 60). | |
| hours | No | Single-line-item total hours. Use exactly one of lines_csv_path or hours. | |
| period | No | Billing period label, e.g. "Jul 21 - Aug 3, 2026". | |
| confirm | No | Set true to actually finalize and send. Omit or false to dry-run only. | |
| customer | No | Stripe customer id (default: swyft market, Inc.). | |
| lines_csv_path | No | Path to a CSV of hours,description rows (one line item each). Use exactly one of lines_csv_path or hours. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully carries the burden. It discloses the dry-run default, the wrapping of send_invoice.py, and the condition for actual sending (confirm:true). This provides clear behavioral expectations beyond what schema alone offers.
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 extremely concise with two sentences: the first defines the primary action, the second details the critical dry-run behavior. Every word is purposeful, and the most important information 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?
Given the 7 optional parameters and no output schema or annotations, the description adequately explains the tool's core functionality and unique behavior (dry-run vs send). It mentions printing totals, which gives insight into the return format. However, it does not cover error handling or prerequisites, but for this tool it is sufficient.
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 does not add significant extra meaning beyond what the parameter descriptions already specify (e.g., default values, mutual exclusivity of lines_csv_path and hours). It confirms the dry-run vs send mechanism tied to confirm, but this is already clear from the schema description.
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 drafts and optionally sends a Stripe invoice, using a specific verb and resource. It distinguishes from sibling tools like stripe_list_recent_invoices by focusing on invoice creation/sending rather than listing or querying.
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 explains the default dry-run behavior and how to make it send via confirm:true, but it does not explicitly state when to use this tool versus sibling tools. Usage context is implied but not contrasted with alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a distinct domain prefix (stripe_, cloudflare_, brain_, model_, client_) and a unique verb+noun combination, ensuring no ambiguity. For example, stripe_send_invoice is clearly separate from stripe_list_recent_invoices.
All tool names follow a consistent pattern of <domain>_<verb>_<noun> in lowercase with underscores. No mixing of conventions like camelCase or different verb styles.
9 tools is well-scoped for an operations server covering multiple subdomains. Each tool serves a clear purpose without redundancy.
The tool set covers core operations for Stripe, Cloudflare, documentation, model routing, and client onboarding. Minor gaps exist (e.g., no Stripe customer creation), but these are explicitly noted as manual steps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client.
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
The bridge from K2 agents through Wrangler to your master AI - safe, approval-gated Cloudflare ops.
Unified gateway exposing 150+ tools across all NexGenData MCP servers via one endpoint.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Gizziio/allternit-ops'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
