exitvalue-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EXITVALUE_DATA_URL | No | Overrides the dataset URL (e.g. to point at a mirror). Optional; no API key or credentials are required. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_industriesA | Read-only. Lists every industry and sub-vertical ExitValue.ai tracks, with ids and display names; ids marked * have published multiples in the open dataset. Takes no input. Use it first when you are unsure of an id; the other tools accept these ids or plain-English names. |
| get_valuation_multiplesA | Read-only. Answers 'what multiple does a business in industry X sell for?' for ONE industry. Returns median EV/EBITDA and EV/Revenue multiples with the middle 50% (25th-75th percentile) and deal count n for each enterprise-value bracket (disclosed deals 2018-2026). Cells with fewer than 10 deals are withheld, never estimated. Passing an industry group id (e.g. 'healthcare') returns a median per sub-vertical. Use compare_industries to put several industries side by side and get_multiples_trend for year-by-year history. Population medians only: it does not value a specific business. |
| compare_industriesA | Read-only. Puts 2-6 industries side by side for one metric: median multiple, middle 50% (25th-75th percentile) and deal count n per enterprise-value bracket, using the same data, name matching and n>=10 threshold as get_valuation_multiples. Pass size_bracket to compare a single deal-size bracket. Industries without enough deals are marked INSUFFICIENT DATA rather than estimated; unmatched names and industry-group ids are flagged per row. Use it for 'which sells for more, X or Y?' questions; use get_valuation_multiples for one industry's full breakdown. |
| get_multiples_trendA | Read-only. Year-by-year history for ONE sub-vertical: for each deal year 2018-2026, the median EV/EBITDA and/or EV/Revenue multiple with middle 50% (25th-75th percentile), deal count n and median deal value, from the open per-year dataset. Only years with at least 10 disclosed deals for a metric are shown; missing years are listed as gaps and never interpolated, so many sub-verticals have few or no years. Use it for 'are multiples rising or falling for X?' questions; use get_valuation_multiples for pooled figures by deal size. |
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 4 tools
Each tool targets a clearly different query shape: taxonomy lookup (list_industries), single-industry breakdown (get_valuation_multiples), multi-industry side-by-side (compare_industries), and time series (get_multiples_trend). The descriptions explicitly cross-reference each other with 'use X instead for Y' guidance, leaving no plausible misselection path.
All names are snake_case verb_noun (list_/get_/compare_ + resource), so the pattern is predictable. Minor deviation: the noun varies between 'valuation_multiples' and 'multiples_trend', and two tools share the generic 'get_' prefix, but intent is still readable.
Four tools map cleanly onto the four natural access patterns of a multiples dataset — enumerate, single, compare, trend — with no filler. The surface is tightly scoped for the server's narrow stated purpose.
Lookup, single-industry breakdown, comparison, and temporal trend are all covered, and name-to-id resolution is handled inside the tools rather than requiring a separate step. Minor gaps: no way to inspect bracket definitions/thresholds, deal-value distributions beyond the median, or filter by deal year within the cross-sectional tools.