Skip to main content
Glama
twalichiewicz

MeshSeeks

by twalichiewicz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CLAUDE_CLI_PATHNoAbsolute path to the Claude CLI executable
MCP_MAX_RETRIESNoMaximum retry attempts for transient errors3
MCP_CLAUDE_DEBUGNoEnable verbose debug loggingfalse
MCP_MESH_TIMEOUTNoAgent execution timeout300000
MCP_MESH_VERBOSENoEnable detailed agent loggingfalse
MCP_USE_ROOMODESNoEnable Roo modes integrationfalse
MCP_RETRY_DELAY_MSNoDelay between retry attempts1000
MCP_WATCH_ROOMODESNoAuto-reload .roomodes on changesfalse
MCP_MESH_MAX_AGENTSNoMaximum concurrent agents5
MESHSEEKS_CATCHPHRASENoEnable or disable MeshSeeks catchphrase
MCP_EXECUTION_TIMEOUT_MSNoTimeout for CLI execution1800000
MCP_HEARTBEAT_INTERVAL_MSNoInterval between progress reports15000

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

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription
healthA

Returns health status, version information, and current configuration of the Claude Code MCP server.

convert_task_markdownB

Converts markdown task files into Claude Code MCP-compatible JSON format. Returns an array of tasks that can be executed using the claude_code tool.

claude_codeA

Claude Code Agent: Your versatile multi-modal assistant for code, file, Git, and terminal operations via Claude CLI. Use workFolder for contextual execution.

• File ops: Create, read, (fuzzy) edit, move, copy, delete, list files, analyze/ocr images, file content analysis └─ e.g., "Create /tmp/log.txt with 'system boot'", "Edit main.py to replace 'debug_mode = True' with 'debug_mode = False'", "List files in /src", "Move a specific section somewhere else"

• Code: Generate / analyse / refactor / fix └─ e.g. "Generate Python to parse CSV→JSON", "Find bugs in my_script.py"

• Git: Stage ▸ commit ▸ push ▸ tag (any workflow) └─ "Commit '/workspace/src/main.java' with 'feat: user auth' to develop."

• Terminal: Run any CLI cmd or open URLs └─ "npm run build", "Open https://developer.mozilla.org"

• Web search + summarise content on-the-fly

• Multi-step workflows (Version bumps, changelog updates, release tagging, etc.)

• GitHub integration Create PRs, check CI status

• Confused or stuck on an issue? Ask Claude Code for a second opinion, it might surprise you!

• Task Orchestration with "Boomerang" pattern └─ Break down complex tasks into subtasks for Claude Code to execute separately └─ Pass parent task ID and get results back for complex workflows └─ Specify return mode (summary or full) for tailored responses

Prompt tips

  1. Be concise, explicit & step-by-step for complex tasks. No need for niceties, this is a tool to get things done.

  2. For multi-line text, write it to a temporary file in the project root, use that file, then delete it.

  3. If you get a timeout, split the task into smaller steps.

  4. Seeking a second opinion/analysis: If you're stuck or want advice, you can ask claude_code to analyze a problem and suggest solutions. Clearly state in your prompt that you are looking for analysis only and no actual file modifications should be made.

  5. If workFolder is set to the project path, there is no need to repeat that path in the prompt and you can use relative paths for files.

  6. Claude Code is really good at complex multi-step file operations and refactorings and faster than your native edit features.

  7. Combine file operations, README updates, and Git commands in a sequence.

  8. Task Orchestration: For complex workflows, use parentTaskId to create subtasks and returnMode: "summary" to get concise results back.

  9. Claude can do much more, just ask it!

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored across 3 tools

Disambiguation5/5

The three tools have completely distinct purposes with no overlap: claude_code handles code/file/Git/terminal operations, convert_task_markdown converts markdown to JSON, and health provides server status. An agent can easily distinguish between them based on their clearly defined scopes.

Naming Consistency2/5

The naming conventions are inconsistent: claude_code uses snake_case but includes a brand name, convert_task_markdown uses snake_case with a descriptive verb-noun pattern, and health is a single lowercase word. There's no unified pattern across the toolset, making it harder to predict naming.

Tool Count3/5

With only 3 tools, the set feels thin for the broad scope implied by claude_code's extensive capabilities (file ops, code, Git, terminal, web search, GitHub integration, etc.). The other two tools are narrow utilities, leaving the main tool overloaded while the overall surface seems underdeveloped for the domain.

Completeness2/5

The toolset is severely incomplete for the implied domain of code/file/Git/terminal operations. While claude_code is a powerful multi-tool, there are obvious gaps: no dedicated tools for specific operations like Git status, file search, or terminal history, forcing everything through one interface. The convert_task_markdown and health tools don't address these core workflow gaps.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources