flru-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FLRU_DEBUG | No | Enable debug logging and artifacts. | false |
| FLRU_DRY_RUN | No | Whether to run in dry-run mode (no real submissions). | true |
| FLRU_DATABASE | No | Path to the SQLite database file. | ./data/flru_mcp.sqlite3 |
| FLRU_HEADLESS | No | Whether to run the browser in headless mode. | true |
| FLRU_STORAGE_STATE | No | Path to the browser storage state file. | ./data/storage_state.json |
| FLRU_BROWSER_PROFILE | No | Path to the browser profile directory. | ./data/browser-profile |
| FLRU_EXPERTISE_PROFILE | No | Path to the expertise profile YAML file. | ./config/expertise.yml |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| flru_auth_statusA | Checks whether the current FL.ru session is authenticated. |
| flru_loginB | Starts a manual Playwright login session and persists browser storage state. |
| flru_list_projectsD | – |
| flru_search_projectsD | – |
| flru_get_projectD | – |
| flru_find_relevant_projectsD | – |
| flru_mark_project_seenD | – |
| flru_get_unseen_projectsD | – |
| flru_get_project_historyD | – |
| flru_get_proposal_contextD | – |
| flru_save_proposal_draftD | – |
| flru_get_proposal_draftD | – |
| flru_submit_proposalD | – |
| flru_list_conversationsD | – |
| flru_get_conversationD | – |
| flru_send_messageD | – |
| flru_get_customerD | – |
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 17 tools
Tools are mostly distinct, each targeting a specific resource (projects, proposals, conversations, customer, auth). However, the project-related tools (find_relevant_projects, get_unseen_projects, list_projects, search_projects) may overlap in purpose, especially without detailed descriptions.
Names generally follow a consistent flru_verb_noun pattern (e.g., flru_get_project, flru_send_message). A few exceptions like flru_login and flru_auth_status deviate slightly, but the overall pattern is predictable and readable.
With 17 tools, this sits in the 16-25 range that feels heavy. The count is justified by the broad scope (auth, projects, proposals, conversations, customer), but some tools may be redundant (multiple project discovery variants), making the set slightly larger than necessary.
The tool surface covers the core workflow from authentication through project discovery, proposal drafting/submission, and client communication. Missing operations like updating/withdrawing proposals or marking conversations read, but the main lifecycle is well represented.