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., "@azdo-onprem-mcp search work items with 'bug' in title"
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.
Minimal Model Context Protocol server for self-hosted Azure DevOps Server (on-premises). It uses the REST APIs with a PAT and Basic auth (curl -u ":$PAT"), same as Azure DevOps Services patterns but with your own base URL.
Not for dev.azure.com only—any DevOps Server reachable over HTTPS works if the APIs respond.
Node.js 18+
A Personal Access Token with at least Work Items (Read) (and any other scopes you rely on)
VPN/network access to your server if required
Related MCP server: Azure DevOps MCP Server
npm install -g azdo-onprem-mcpOr run without a global install:
npx azdo-onprem-mcpThe package exposes the CLI binary azdo-onprem-mcp (see package.json → bin).
Variable | Required | Description |
| Yes | Team project root URL, same as in the browser for that project, e.g. |
| Yes | Personal Access Token. Sent as Basic auth with an empty username ( |
| No | Overrides collection root for |
| No | HTTP timeout in ms (default |
| No | REST |
| No | Set to |
Do not commit secrets. Prefer Cursor/IDE env injection or your OS secret store.
Example mcp.json entry using the published package (-y lets npx install or run without an interactive prompt, which MCP clients need):
{
"mcpServers": {
"azdo-onprem": {
"command": "npx",
"args": ["-y", "azdo-onprem-mcp"],
"env": {
"AZURE_BASE_URL": "https://devops.example.com/Collection/MyProject",
"AZURE_PAT": "<your-pat>"
}
}
}
}Alternatives
Global install: "command": "azdo-onprem-mcp" with no args (or an empty args array), if npm install -g azdo-onprem-mcp put the binary on your PATH.
Local clone: after npm install and npm run build, use "command": "node" and "args": ["/absolute/path/to/azdo-onprem-mcp/dist/server.js"] (adjust the path to your machine).
Reload MCP / restart the editor after changing env.
Windows / npx: From v1.0.1, HTTP calls use Node’s built-in fetch only (the axios dependency was removed). That avoids a known failure where npx pulled a broken tree and mime-db could not load db.json. If you still see strange missing-module errors, run npm cache clean --force and try again.
Tool | Description |
|
|
| WIQL search on |
|
|
Mac/Linux: use single quotes around the URL so $expand is not interpreted by the shell.
export AZURE_PAT='your-pat'
curl -sS -u ":$AZURE_PAT" \
'https://your-host/Collection/MyProject/_apis/wit/workitems/12345?$expand=all&api-version=7.1'From a clone of this repository:
npm install
npm run build
npm startSource lives in src/ (TypeScript); npm run build emits to dist/. With AZURE_BASE_URL and AZURE_PAT set, npm start runs the MCP server on stdio (stop with Ctrl+C). Point your MCP client at this command or use npx azdo-onprem-mcp after publishing.
From the repo root (with npm login if needed):
npm run build
npm publishprepack runs npm run build automatically, so dist/ is always fresh in the tarball. For a scoped package name (e.g. @your-scope/azdo-onprem-mcp), use npm publish --access public the first time.
MIT (see package.json → "license").
Returns the complete Azure DevOps work item JSON from GET /_apis/wit/workitems/{id}?$expand=all. Includes the full fields map (System.Title, System.Description, System.Tags, custom fields, etc. — only fields with values are present), relations, _links, rev. This is NOT limited to id/title/state/assignedTo; read the fields object for description, tags, and links.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden and excels: it details the exact response structure ('full fields map', 'relations', '_links', 'rev'), notes that only populated fields appear, and explicitly warns against expecting only basic fields. This adds significant behavioral context beyond the mere fact it 'gets' a work item.
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 three sentences, each earning its place: the first states the core purpose, the second details the response contents, and the third clarifies scope. It is front-loaded and compact with no fluff.
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 one-parameter GET with no output schema and no annotations, the description is thorough: it names the endpoint, explains the included fields, and clarifies the absence of certain fields. It also differentiates from siblings, making it complete for its complexity.
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 has zero descriptions, so the description must compensate. It does by embedding 'id' in the API path, indicating it's the work item identifier. However, it doesn't elaborate on the type or constraints beyond the schema's integer and exclusiveMinimum, so it slightly over-delivers but leaves a little room for more.
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+resource: 'Returns the complete Azure DevOps work item JSON from GET /_apis/wit/workitems/{id}?$expand=all.' It clearly states the exact API endpoing and the scope of data returned, distinguishing it from sibling tools like searchWorkItems by emphasizing it's not limited to a subset of fields.
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 this when you need the full work item JSON for a known ID. The phrase 'This is NOT limited to id/title/state/assignedTo' suggests that if you only need those basic fields, other tools may suffice, but it doesn't explicitly name alternatives or state when-not-to-use. So it provides clear context without exclusions, fitting score 4.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List team projects in the Azure DevOps collection. Uses AZURE_COLLECTION_URL if set, otherwise derives collection URL from AZURE_BASE_URL.
| 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 of behavioral disclosure. It does add useful context about environment variable fallback (AZURE_COLLECTION_URL vs AZURE_BASE_URL), which is a behavioral trait. However, it does not disclose the return format, pagination, or any authentication requirements, leaving gaps in transparency for a tool with no 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 two short sentences, front-loaded with the action and resource, and contains no superfluous words. It efficiently conveys the core purpose and a configuration detail without waste.
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 tool's simplicity (0 params, no output schema), the description covers the main purpose and adds a useful configuration note. However, it does not explicitly describe what the response includes (e.g., project IDs, names), which would be expected when no output schema exists. It is nearly complete but lacks that minor detail, so a 4 is appropriate.
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 tool has zero parameters, so the description has nothing to explain. The baseline for 0 parameters is 4, and the description correctly avoids adding any unnecessary parameter details.
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 'List' and the resource 'team projects in the Azure DevOps collection,' which is specific and unambiguous. It naturally distinguishes from sibling tools (getWorkItem, searchWorkItems) that deal with work items, not projects.
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 clear context for when to use the tool: when you need to list team projects in the collection. It does not explicitly mention alternatives or exclusions, but the sibling tools are sufficiently different that the intended usage is obvious. No misleading guidance is present.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search work items whose title contains the given text (WIQL CONTAINS on System.Title). Returns { id, title, state }[].
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of disclosure. It specifies the underlying WIQL CONTAINS operation and the return shape, but does not explicitly state that the operation is read-only or describe any error/empty-result behavior. It adds some useful detail beyond a bare purpose 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 a single, focused sentence that front-loads the action and resource, followed by a compact return type note. Every word contributes value with no fluff.
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 one parameter and no annotations, the description provides the essential information: what it searches, how it searches (WIQL CONTAINS), and what it returns. The output schema is absent but the return shape is explicitly given, making the description self-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?
The schema has one parameter ('query') with 0% description coverage, so the description must compensate. It clarifies that the query is 'the given text' to search for in the title, which adds meaning beyond the raw parameter name. However, it doesn't add details like case sensitivity or wildcard support.
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 searches work items by title text, using a specific verb ('Search') and resource ('work items'). It distinguishes from siblings by focusing on title-based search rather than listing projects or fetching a single work item.
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 a search use case, but provides no explicit guidance on when to use this tool versus alternatives like getWorkItem or listProjects. There are no prerequisites, exclusions, or context about when search is preferred.
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.
v1.0.2getWorkItemlistProjectssearchWorkItemsEach tool targets a distinct resource/action: listProjects for projects, getWorkItem for a specific work item by ID, and searchWorkItems for finding work items by title. No overlap in functionality.
All tool names follow a consistent verb_noun pattern in camelCase: listProjects, getWorkItem, searchWorkItems. The naming is predictable and uniform.
With only three tools, each serves a clear and non-redundant purpose. The count is well-scoped for a focused Azure DevOps read-only server.
The tool surface is severely limited, providing only read operations. There is no ability to create, update, or delete work items, nor any support for queries beyond title-based search. Significant gaps exist for a typical Azure DevOps integration.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
The MCP server for Azure DevOps, bringing the power of Azure DevOps directly to your agents.
An MCP server that provides access to Testiny projects, test cases and test runs
An MCP server that let you interact with Cycloid.io Internal Development Portal and Platform
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ajithnow/azdo-onprem-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
