mba-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| add_target_companyA | Add a company to the target list. Paste the company's careers or job-board URL as ats_url and the board is resolved automatically (Greenhouse, Lever or Ashby). Without one, job search for this company falls back to Adzuna if it is configured. |
| list_targetsA | List every target company, highest priority first. |
| find_jobsC | Find open roles on target companies' job boards. |
| track_applicationA | Add a role to the application pipeline. This tracks an application; it never submits one. Pass jd_text when the user has the posting to hand — storing it means you can tailor their CV against the real requirements later instead of guessing at what the firm asked for. |
| update_applicationB | Move an application along the pipeline or revise its deadline/notes. |
| list_applicationsB | The pipeline, soonest deadline first, with a count per status. |
| get_recruiting_timelineA | Key dates for a recruiting track, projected onto the current cycle. Dates are a curated template of a typical calendar, not live firm deadlines — tell the user to confirm against their career centre. |
| import_connectionsA | Import the user's own LinkedIn connections export (Connections.csv). Re-running is safe: contacts are matched on name plus company and updated in place. |
| find_warm_pathsA | Rank stored contacts by how warm a path they are into a company. Scoring is transparent: each result carries the reasons behind its score (same employer, alum of your school, recruiting-side role, prior interactions, recency of the connection). |
| log_interactionB | Log a touchpoint with a contact and set when to circle back. |
| get_followupsA | Contacts owed a follow-up, most overdue first. |
| save_outreach_draftA | Store an outreach email you have written for a contact. Nothing is sent here. Show the draft to the user, revise it with them, then call send_email with confirm=True once they approve. |
| send_emailA | Send exactly one saved draft from the user's own Gmail account. Requires confirm=True, which stands for an explicit human yes to this specific message. One call sends one email; never loop this tool over a list of contacts. |
| set_profileA | Save who the user is. Ask for this once, at the start. School and graduation year make alumni outreach work. Background, goals and constraints are what let you judge fit properly instead of guessing — fill them in from what the user tells you in conversation, not by interrogating them. Only the fields you pass are changed. |
| list_target_packsB | Curated starter lists of firms, one per track. |
| add_target_packA | Add a whole track's worth of target firms at once. Each firm's job board is resolved from its careers page as it is added, so find_jobs works immediately for the firms that have a readable board. |
| find_alumniA | Find people from the user's school to reach out to, at a target firm. Returns two things: alumni already in their imported contacts, and ready-made LinkedIn searches for the ones they have not met yet. This server never reads LinkedIn — the user opens the search links themselves, connects as a human, and re-imports their export to turn new connections into warm paths. |
| suggest_emailA | Work out a contact's likely work email from addresses already on file. Learns each firm's convention from colleagues whose addresses you already have. Every result is an unverified guess — show it to the user, let them sanity-check it, and expect a bounce sometimes. |
| set_contact_emailA | Save a confirmed email address on a contact. |
| save_resumeA | Store the user's CV so it can be tailored against real postings. The user pastes it straight into the chat — no files, no folders. Replaces whatever was stored before, so read the current one back first if you are only editing part of it. |
| add_resume_noteA | Capture something that happened since the CV was last written. A case competition win, a new leadership role, a project that finished. These accumulate so the CV can be refreshed properly later, and so you can draw on recent material the CV does not mention yet. |
| weekly_checkinA | Everything that needs attention this week, in one call. This is the habit: what is overdue, what closes soon, who has gone quiet, which target firms nobody has spoken to yet, and where the user sits in the cycle. The numbers are facts — the coaching is yours. Lead with the two or three things that actually matter, not the whole list. |
| suggest_targetsA | Firms worth considering, with the evidence needed to judge fit. Returns candidates the user has not targeted yet, each annotated with what is actually known: whether their job board can be read, and how many of the user's own contacts already work there. Judge fit yourself against their resume and background — this tool deliberately does not score it, because "suits my profile" is a judgement about a person, not a lookup. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| start_here | Set up the campaign from scratch, in one conversation. |
| catch_me_up | The Monday-morning coaching session. (The weekly_checkin tool feeds it.) |
| fit_check | Which firms actually suit me, and where am I stretching? |
| tailor_application | Tailor the CV and application material to one specific posting. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| resume_resource | The user's CV, plus everything that has happened since it was written. |
| base_cv | Deprecated alias for the resume resource. |
| profile_resource | Who the user is: school, graduation year, track. |
| targets_resource | Current target company list. |
| pipeline_resource | Current application pipeline with deadline countdowns. |
| contacts_resource | Imported contacts and their follow-up state. |
| timeline_resource | Key dates for the user's track, projected onto this cycle. |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/nhemrajani/mba-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server