AI Company Manager MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| COMPANY_DATA_DIR | No | Directory where company data is stored. Can be absolute or relative to the project root. | company_data |
| COMPANY_MAX_FILE_MB | No | Maximum allowed file size in MB for reading and writing. Must be at least 1. | 10 |
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 |
|---|---|
| list_company_filesA | List all files in company_data with type, byte size, and modification time. |
| get_company_overviewA | Return a current company profile and financial summary from local files. |
| read_company_fileB | Read a supported company TXT, MD, JSON, CSV, XLSX, PDF, or DOCX file as text. |
| create_new_companyB | Create a new company profile, financial ledger, and founder employee record. |
| add_financial_recordC | Append an income or expense transaction to financials.json. |
| add_employeeC | Append a validated employee record to employees.csv. |
| inspect_company_dataB | Check whether the files in company_data match the schema the tools expect. |
| migrate_company_dataA | Convert an existing employees.csv to the current column schema. Runs as a dry run by default. With apply=True it renames the known columns, fills in start_date/status defaults, keeps unknown columns such as performance_score, and writes a timestamped backup first. |
| plan_company_data_migrationA | Propose how to map an existing company_profile.json and financials.json. Read-only: nothing is written. Reports which source fields are already valid, which ones can be mapped and how, which information would be dropped, and the questions that must be answered before the data can be migrated. |
| apply_company_data_migrationA | Write a confirmed company_profile.json and financials.json mapping. Pass one answer per open item reported by plan_company_data_migration, keyed by its key (for example "company_profile.json:mission"). An answer of true accepts the proposed value; any other answer is used as the final value. Runs as a dry run unless apply=True, and backs up each changed file first. |
| update_company_notesC | Create or update a company policy, meeting, strategy, or vision note. |
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 11 tools
Most tools have distinct purposes, but the migration surface is muddled: migrate_company_data (employees.csv) vs plan_company_data_migration and apply_company_data_migration (company_profile.json/financials.json) split similar work across overlapping tools, making misselection easy. update_company_notes also partially overlaps with create_new_company's profile creation.
Nearly all tools follow a consistent verb_noun snake_case pattern (add_employee, list_company_files, create_new_company). Minor deviation: some names carry the redundant 'company' prefix (read_company_file, inspect_company_data) while others don't (add_employee, add_financial_record), but the style remains readable and predictable.
11 tools is a reasonable, well-scoped set for a file-based company manager. Slight bloat in the migration area—three plan/apply/migrate tools address essentially one concern—but overall each tool earns its place.
Creation and read paths are covered (create_new_company, add_employee, add_financial_record, read/list/inspect files), but there are no update or delete operations for employees or financial records, and no way to edit the company profile after creation. These gaps in the lifecycle will force agents to fall back on raw file writes.