mcp-flow
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| inspect_projectA | Analyze a project's structure: directory tree, detected stack(s), package manager, available scripts, presence of tests/linter/typechecker, and notable config files. Read-only. |
| read_relevant_filesA | Read the files most relevant to a task without loading the whole project. Either pass candidateFiles, or let the tool rank files by lexical relevance. Content is truncated, secret-masked, and sensitive files are skipped by default. Read-only. |
| create_change_planA | Assemble a structured change plan from deterministic project context (likely files, checks to run, detected risks) before writing code. Returns a plan scaffold plus guidance for finalizing it. Makes a reasonable assumption rather than asking unless something is truly blocking. Read-only. |
| generate_patchA | Turn concrete |
| apply_patchA | Apply a unified diff to the project. Defaults to dryRun=true. All target paths are confined to the project root, suspicious mass deletions are refused, and touched files are backed up before writing. Validates that every hunk applies cleanly first. |
| run_project_checksA | Auto-detect and run the project's test / lint / typecheck / build commands. Only allowlisted base commands are spawned; each runs in the project dir with a timeout, bounded and secret-masked output. |
| analyze_check_failuresA | Parse test / lint / typecheck / build output into structured issues (file, line, code, message, priority), identify affected files, and return guidance for producing a corrective patch. Read-only. |
| fix_loopA | Run a controlled verify→analyze→fix loop. Each iteration runs the project checks; on failure it analyzes errors and, when the client supports MCP sampling, requests corrective edits and applies them (if allowApply=true), then re-checks — up to maxIterations. Every action taken is reported. When sampling is unavailable it returns a precise advisory so the calling assistant can drive the loop. |
| git_statusA | Report the Git state: current branch, staged/modified/untracked files, last commit, and whether the working tree is clean. Read-only. |
| summarize_changesA | Produce a clean summary of changes: a user-facing summary, a technical summary, a suggested conventional-commit message, the checks performed, and known limitations. Uses the current git diff when none is supplied. Read-only. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/remimenguy/mcp-flow'
If you have feedback or need assistance with the MCP directory API, please join our Discord server