Present Agent MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PRESENT_AGENT_CLIENT | No | Client label for attribution (e.g. claude-code, codex). | unknown |
| PRESENT_AGENT_API_BASE | No | API base. Change only if self-hosting Present Agent. | https://presentagent.vip |
| PRESENT_ENABLE_LOCAL_AGENT_CONTEXT | No | Allow opt-in local context search (still needs useAgentContext=true). | |
| PRESENT_EXPOSE_LOCAL_AGENT_CONTEXT_LINES | No | Echo extracted local lines in the response (debug only). |
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 |
|---|---|
| present_find_giftA | Find 5 personalized gifts through the hosted Present Agent API. Optional local Claude/Codex context search is opt-in. |
| present_beta_startA | Return the fastest beta onboarding instructions and live web fallback. |
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 2 tools
The two tools have clearly distinct purposes: one provides beta onboarding instructions, the other finds personalized gifts. There is no overlap in functionality.
Both tools follow a consistent verb_noun pattern with the 'present_' prefix, making it easy to understand their actions at a glance.
With only 2 tools, the server feels underdeveloped for an 'agent' service. While each tool has a specific function, the overall scope is limited.
The tool surface is minimal, missing obvious operations like getting more details on gifts, managing user preferences, or iterating on results. Agents are left with limited functionality.