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., "@Public Gateway MCP show me the latest backup status"
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.
Public Gateway MCP connects your favorite AI assistants directly to Axcient. Ask questions, pull insights, and take action — all through natural conversation. No dashboards to hunt through. No context switching. Just answers. 🚀
🔌 Plug and play — Drop it into Cursor, Claude Desktop, or any MCP-compatible client and go.
📡 Real data, real time — Your AI tools work with live Axcient information, not stale snapshots.
🛠️ Built for builders — Designed for teams who want their agents to do things, not just talk about them.
Related MCP server: Vectra AI MCP Server
git clone https://github.com/axcient/public-gateway-mcp.git
cd public-gateway-mcp
direnv allowAdd your Axcient API key to the .env file:
API_KEY="your-api-key-here"just runThat's it. Your MCP server is live. 🎉
Add Public Gateway MCP to your MCP client configuration and point it at the running server. Once connected, your assistant can interact with Axcient on your behalf.
💡 Tip: Restart your AI client after adding the server so it picks up the new tools.
Use just for everything — install, run, lint, and checks:
just # see available commands
just fix # auto-fix lint/format issues
just check-all # full project check before you shipAdd two numbers Axcient way
| Name | Required | Description | Default |
|---|---|---|---|
| a | Yes | ||
| b | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations present; description only states 'add', implying a pure computation, but lacks details on error behavior, overflow, or return format. Minimal behavioral 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?
Single sentence is concise, but the phrase 'Axcient way' is unnecessary and unclear. Adequate but could be more structured.
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 tool with output schema, the description is too minimal. It does not explain outputs or provide sufficient context for an AI agent to use it effectively.
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% and description adds no parameter meaning beyond type hints. 'Add two numbers' does not explain what parameters 'a' and 'b' represent or how the default for 'b' is used.
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 verb 'add' and resource 'two numbers' clearly state the core operation. It distinguishes from sibling tools like get_billable_usage and get_client_info, which are unrelated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool or alternatives. Siblings are unrelated, but the description provides no context or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get billable usage report for specified date range If not provided, it'll return current month's usage data It returns list of client usage in the children field
| Name | Required | Description | Default |
|---|---|---|---|
| end_date | No | ||
| start_date | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses default date range and output structure (list in children field), but lacks details on auth, rate limits, or error cases.
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 concise sentences with clear structure: purpose, default behavior, output explanation. No redundant information.
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 2 optional params, no annotations, and existing output schema, the description covers purpose, default, and output field. It is mostly complete, though could mention response type briefly.
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 description compensates partially. It explains that optional start_date and end_date default to current month, but does not add detail on constraints or format beyond 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 it gets a billable usage report for a date range. It specifies the resource and verb, and differentiates from siblings 'add' and 'get_client_info'.
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 explains when to use (specified date range, else current month) and implies default behavior. However, it does not explicitly state when not to use or compare to alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get billable usage report for specified date range If not provided, it'll return current month's usage data
| Name | Required | Description | Default |
|---|---|---|---|
| client_id | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description claims it returns a billable usage report but contradicts the tool name. It mentions date range functionality that isn't supported by the input schema, creating confusion about 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?
Only two sentences, but they are misleading and lack clarity. The phrase 'If not provided' is ambiguous and does not correspond to any parameter, making the description inaccurate rather than concise.
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 name vs. description mismatch, missing date range parameter, and lack of behavioral disclosure, the description fails to provide sufficient context for a tool with one required parameter and an output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description fails to explain the sole parameter 'client_id'. It mentions 'specified date range' but no such parameter exists, directly contradicting the schema. With 0% schema description coverage, the description provides no meaningful parameter guidance.
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 name 'get_client_info' suggests retrieving general client information, but the description says 'Get billable usage report for specified date range,' which is a mismatch. The sibling tool 'get_billable_usage' likely handles billable usage, causing confusion about this tool's role.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs. alternatives like 'get_billable_usage'. The description implies a default date range but is vague, leaving the agent unsure of the intended use.
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.
v0.1.0addget_billable_usageget_client_infoTwo tools (get_billable_usage and get_client_info) have identical descriptions, making them indistinguishable. The add tool is unrelated, but the overlap between the other two is severe.
Naming pattern is inconsistent: 'add' does not follow the 'get_' prefix of the other tools. Additionally, get_client_info has a misleading name given its description duplicates get_billable_usage.
3 tools is borderline low but could be acceptable for a very narrow domain. However, the duplication reduces effective count to 2, making the set feel incomplete.
The server's purpose is unclear, but the limited scope (addition and two identical usage reports) suggests significant gaps. No update, delete, or list operations for clients or usage data.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Connect any AI assistant to Syncro: manage tickets, invoices, customers, assets, and more.
Connects AI assistants to CloudQuell multi-cloud and AI cost, savings, anomaly, and budget data.
Integrate Connext AI into agentic workflows, enabling Connext product-aware assistance.
Connect Exact Online to your AI assistant via MCP. Manage Exact Online with natural language.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Axcient/public-gateway-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
