Generates branch names, validates commit messages, and drafts pull request bodies following conventions, designed to automate the Jira issue to PR lifecycle.
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., "@mcp-dev-workflow generate a branch name for feature ABC-123: Add login"
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.
An MCP server that gives AI assistants (Claude, Cursor, …) a set of deterministic, convention-enforcing tools to standardize the development workflow from issue to pull request.
These are the kind of tools an assistant calls to do something precise — generate a branch name, validate a commit, draft a PR body — rather than free-form generation. Same input, same output, every time.
Public, runnable distillation of an AI-agent workflow I built to automate the Jira issue → PR lifecycle.
Tool | What it does |
| Turn |
| Validate & normalize a Conventional Commit; returns |
| Turn a list of commits (and optional changed files) into a Markdown PR body: summary, changes grouped by type, and a checklist. |
Every tool exposes a JSON Schema for both its input and its output (structured content), so capable clients get typed results, not just text.
Related MCP server: DevFlow MCP Server
The server runs over stdio and needs no install — point your MCP client at it
via npx.
Edit claude_desktop_config.json
(macOS: ~/Library/Application Support/Claude/,
Windows: %APPDATA%\Claude\):
{
"mcpServers": {
"dev-workflow": {
"command": "npx",
"args": ["-y", "@sergiorodas/mcp-dev-workflow"]
}
}
}Add to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):
{
"mcpServers": {
"dev-workflow": {
"command": "npx",
"args": ["-y", "@sergiorodas/mcp-dev-workflow"]
}
}
}Restart the client and the three tools appear. Requires Node 18+.
branch_nameGenerate a git branch name from a change type, ticket id and title.
Param | Type | Default | Notes |
| enum | — |
|
| string | — | Ticket id, e.g. |
| string | — | Short title, slugified (lowercased, accents stripped). |
| string |
| Joins id and slug, and words within the slug. |
| number | — | Optional cap; the slug is truncated to fit. |
// in: { "type": "feat", "id": "ABC-123", "title": "Add login" }
// out: "feat/ABC-123-add-login"commit_messageValidate and normalize a Conventional Commit (type(scope): subject).
Param | Type | Default | Notes |
| string | — | Commit message; the first line is the header. |
| string[] | the 11 types above | Override the accepted types. |
| number |
| Max subject length. |
| boolean |
| Make |
Checks the header format, the type, subject length, a trailing period, and hints
at non-imperative mood. Returns { valid, normalized, errors, warnings, parsed }.
// in: { "message": "feat(auth): added login." }
// out: {
// "valid": true,
// "normalized": "feat(auth): added login",
// "warnings": [
// "Subject should not end with a period.",
// "Use the imperative mood in the subject (e.g. 'add' instead of 'added'/'adds')."
// ],
// "parsed": { "type": "feat", "scope": "auth", "breaking": false, "subject": "added login" }
// }pr_checklistBuild a Markdown PR body from a list of commits.
Param | Type | Default | Notes |
| string[] | — | Commit messages (or just their headers). |
| string[] |
| Optional file list to include. |
| string | — | Optional |
Groups commits by conventional type, detects breaking changes (! or a
BREAKING CHANGE: footer), and emits a tests/docs/breaking-changes checklist.
## Summary
<!-- Describe what this PR does and why. -->
2 commits across 2 areas.
## Changes
### Features
- add login **(auth)**
### Fixes
- handle null user
## Checklist
- [ ] Tests added or updated
- [ ] Documentation updated
- [x] No breaking changes
- [ ] Self-reviewed the diffThis project dogfoods the conventions it preaches.
npm install
npm run dev # run the server from source (tsx)
npm run typecheck # tsc --noEmit
npm test # vitest
npm run build # tsup -> dist/Architecture: pure logic lives in src/lib/ as plain,
unit-tested functions with no MCP coupling; src/tools/ wraps
each one in an MCP tool definition with a zod schema;
src/index.ts registers them on the stdio server.
MIT © Sergio Rodas
Generate a convention-following git branch name from a change type, ticket id and title. Example: {type:'feat', id:'ABC-123', title:'Add login'} => feat/ABC-123-add-login.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Issue / ticket id, e.g. ABC-123. Case is preserved. | |
| type | Yes | Change type, used as the branch prefix (e.g. feat, fix, chore). | |
| title | Yes | Short human-readable title, e.g. 'Add login screen'. | |
| maxLength | No | Optional max length for the whole branch name (slug is truncated to fit). | |
| separator | No | Separator used inside the slug and between id and slug. | - |
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| slug | Yes | |
| type | Yes | |
| branch | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the transparency burden. It shows one example output but doesn't disclose edge-case behavior (e.g., slugification rules, truncation, handling of special characters). The schema mentions truncation for maxLength, but the description itself doesn't add behavioral context beyond the example.
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, information-dense sentence followed by a high-value example. Every word earns its place, and the example greatly improves comprehension without extra 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 straightforward generation tool with an output schema, the description covers the core functionality and output format via example. It doesn't explain the exact convention rules in detail, but the example sufficiently conveys the expected behavior for most use cases.
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 provides 100% parameter coverage with detailed descriptions, so the baseline is 3. The description adds value by showing how type, id, and title combine in the example, but it doesn't elaborate on maxLength or separator beyond what the schema states.
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 ('Generate') and resource ('git branch name'), clearly stating the inputs (change type, ticket id, title). The concrete example disambiguates the exact behavior and distinguishes it from sibling tools like commit_message and pr_checklist.
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 makes it obvious when to use this tool (any time a branch name is needed) and provides an example that shows the transformation. It doesn't explicitly name alternatives, but the sibling tools serve clearly different purposes, so the usage context is clear without exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Validate and normalize a Conventional Commit message (type(scope): subject). Returns { valid, normalized, errors, warnings, parsed } and flags type, length and imperative-mood issues.
| Name | Required | Description | Default |
|---|---|---|---|
| message | Yes | The commit message to validate (first line is the header). | |
| allowedTypes | No | Commit types accepted by the project. | |
| requireScope | No | Whether a scope, e.g. (auth), is mandatory. | |
| maxSubjectLength | No | Maximum allowed length of the subject. |
| Name | Required | Description |
|---|---|---|
| valid | Yes | |
| errors | Yes | |
| parsed | Yes | |
| warnings | Yes | |
| normalized | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and it discloses key behaviors: validation, normalization, returning structured fields, and flagging specific issue categories (type, length, imperative mood). It does not mention side effects or authorization, but as a read-only validation tool this is acceptable, and the return details provide meaningful transparency.
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 the main action, and every phrase adds value—return shape and validation flags are included without redundant explanation.
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 moderate complexity and the presence of an output schema, the description adequately covers the tool's purpose and behavior. It could mention broader context (e.g., intended workflow) but that's not essential for correct invocation.
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 all parameter meanings are already available in the schema. The description adds no additional parameter-level details beyond that, so it meets the baseline for high coverage.
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 'validate and normalize' and explicitly references the Conventional Commit format, which clearly distinguishes it from sibling tools branch_name and pr_checklist. It also outlines the return structure, leaving no ambiguity about the tool's core function.
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 intended use case is implied by the description—validating commit messages—but there is no explicit guidance on when to choose this over branch_name or pr_checklist. No exclusions or alternatives are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Build a Markdown pull-request body from a list of commits (and optional changed files): a summary, a change list grouped by conventional type, and a checklist (tests, docs, breaking changes).
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | Optional PR title, rendered as a top-level heading. | |
| commits | Yes | Commit messages (or at least their header lines) in the PR. | |
| changedFiles | No | Optional list of changed file paths to include in the body. |
| Name | Required | Description |
|---|---|---|
| body | Yes | |
| breaking | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the full burden of behavioral disclosure. It states what the tool generates (summary, change list grouped by conventional type, checklist) but does not explicitly confirm whether the tool has side effects (e.g., only produces text vs. modifying PRs) or mention error conditions. This is a moderate gap given the absence of annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that efficiently front-loads the verb and resource, then defines inputs and output structure. Every clause provides useful information without redundancy, making it easy to scan and understand.
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 presence of an output schema covers return values, and the description adequately explains the tool's function and the composition of the generated Markdown. It doesn't mention preconditions or edge cases, but for a generative tool with no annotations, this is reasonably 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?
The input schema already provides descriptions for all three parameters, and the description adds context by explaining how commits contribute to the summary/change list and how changedFiles affect the body. However, it essentially restates the parameter purposes without adding new semantic detail, so the baseline 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 uses a specific action verb 'Build' and identifies the resource as a 'Markdown pull-request body' with clear inputs ('a list of commits' and optional 'changed files'). This clearly differentiates it from sibling tools like branch_name and commit_message, which focus on naming conventions rather than PR content generation.
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 the primary use case—generating a PR body from commits—and the optional changedFiles parameter hints at when to include additional context. It does not explicitly mention when not to use the tool or name alternatives, but the sibling tools serve obviously distinct purposes, making the selection context reasonably clear.
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.
v0.1.0branch_namecommit_messagepr_checklistEach tool targets a distinct stage of the development workflow: branch name generation, commit message validation/normalization, and PR checklist construction. There is no overlap in purpose, so an agent can easily select the right tool based on the task.
All tool names follow the same lowercase_with_underscore pattern and are noun phrases indicating the artifact they handle: branch_name, commit_message, pr_checklist. This consistent convention makes the API predictable and easy to navigate.
With only three tools, the server is tightly scoped to a specific development workflow without unnecessary clutter. Each tool serves a clear, non-redundant purpose within that scope, making the count appropriate for the server's stated function.
The tools cover the essential lifecycle of a conventional development workflow: creating a branch, validating commit messages, and assembling a pull request. A minor gap is the lack of a tool to generate a commit message from a diff, but the validation tool provides sufficient coverage for enforcing conventions.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
MCP server for building and testing AI agents with multi-model experimentation and insights.
The OpenZeppelin Solidity Contracts MCP server integrates OpenZeppelin's security and style rules into AI-driven development workflows, enabling AI assistants to generate safe, correct, and production-ready smart contracts. It automatically validates generated code against OpenZeppelin standards (including imports, modifiers, naming conventions, and security checks) and supports various contract types including ERC-20, ERC-721, ERC-1155, Stablecoins, RWA, Governor, and Account contracts through prompt-driven workflows.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/SergioRodas/mcp-dev-workflow'
If you have feedback or need assistance with the MCP directory API, please join our Discord server