ReplyFlow MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | No | OpenAI API Key (optional, alternative LLM) | |
| TWITTER_API_KEY | Yes | Twitter Consumer Key | |
| ANTHROPIC_API_KEY | No | Anthropic API Key (optional, for AI reply generation) | |
| TWITTER_API_SECRET | Yes | Twitter Consumer Secret | |
| TWITTER_ACCESS_TOKEN | No | OAuth 1.0a Access Token (optional) | |
| TWITTER_ACCESS_TOKEN_SECRET | No | OAuth 1.0a Access Token Secret (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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| replyflow_listD | – |
| replyflow_generateD | – |
| replyflow_copyD | – |
| replyflow_update_configD | – |
| replyflow_config_statusD | – |
| replyflow_switch_accountD | – |
| replyflow_historyD | – |
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 7 tools
No tool descriptions are provided, making it impossible for an agent to distinguish between tools. The tool names alone are too vague and overlapping, e.g., 'copy', 'generate', and 'history' could refer to many different operations.
All tool names share the 'replyflow_' prefix, which is consistent, but the naming pattern varies: some are single verbs ('copy', 'generate', 'list'), some are nouns ('history'), and others are verb_noun ('switch_account', 'update_config') or noun_noun ('config_status') combinations. This mixed pattern reduces predictability.
With 7 tools, the count is well within the typical range of 3–15 tools, suggesting a focused and manageable scope for the server.
Based solely on tool names, there is no obvious create or delete operation, which are common in many domains. The lack of descriptions makes it impossible to assess completeness, but the set appears to have significant gaps for a typical workflow tool.