dispersl-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DISPERSL_API_KEY | Yes | Your Dispersl API key for authentication. | |
| DISPERSL_GIT_MODEL | No | Default model for the git agent (optional). | |
| DISPERSL_CHAT_MODEL | No | Default model for the chat agent (optional). | |
| DISPERSL_CODE_MODEL | No | Default model for the code agent (optional). | |
| DISPERSL_DOCS_MODEL | No | Default model for the docs agent (optional). | |
| DISPERSL_PLAN_MODEL | No | Default model for the plan agent (optional). | |
| DISPERSL_TEST_MODEL | No | Default model for the test agent (optional). |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| dispersl_plan_agentC | Multi-agent task dispersion using agentic execution (plan agent). Agent choices can either be use 'code', 'test', 'git', 'docs' as the agent choices |
| dispersl_code_agentC | Generate code files and codebases based on a prompt using agentic execution |
| dispersl_testing_agentC | Generate end to end tests based on a prompt using agentic execution |
| dispersl_git_agentC | Execute codebase versioning operations with Git based on a prompt using agentic execution |
| dispersl_new_docs_agentC | Generate file by file technical documentation for a code repository using agentic execution |
| dispersl_chat_agentC | Chat with the Dispersl agent to get knowledge or insights about codebases using agentic execution |
| start_sessionC | Start a new agentic session |
| add_mcp_serverC | Connect to an external MCP server and save to config |
| remove_mcp_serverC | Disconnect from an MCP server and remove from config |
| list_modelsC | List available models |
| get_keysB | Get API keys for the authenticated user |
| new_keyB | Generate new API key |
| create_taskC | Create a new task |
| edit_taskC | Edit a task by ID |
| get_tasksC | Get all tasks |
| get_taskC | Get a task by ID |
| cancel_taskC | Cancel a task by ID |
| edit_stepC | Edit a step by ID |
| get_stepsC | Get all steps |
| get_stepC | Get a step by ID |
| cancel_stepC | Cancel a step by ID |
| get_usage_statsD | Get usage stats |
| get_language_statsC | Get language usage stats |
| get_agent_statsC | Get agent query stats |
| get_task_historyC | Get task history by ID |
| get_step_historyC | Get step history by ID |
| fetch_api_rootB | Fetch API root (utility endpoint) |
| health_checkC | Health check endpoint |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 28 tools
Most tools target distinct resources and actions, especially task/step CRUD, stats, and specialized agents. Minor ambiguity exists between the plan agent and specialized agents, and history/current getters require attention to descriptions.
The set uses consistent snake_case and mostly follows a verb_noun pattern. Minor deviations like new_key vs create_task, fetch_api_root, and the dispersl_* agent prefixes are readable but not perfectly uniform.
28 tools is heavy for a single MCP server, spanning tasks, steps, stats, agents, sessions, MCP configuration, models, and API keys. While many are distinct, the surface is large enough that consolidation or clearer grouping would improve usability.
Core task, step, agent, and key operations are present, but lifecycle coverage has notable gaps. There is no create_step, no delete/revoke for tasks, steps, or keys, no list MCP servers, and no session termination.