Engagement MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ENGAGEMENT_ROOT | Yes | Absolute path to the engagement root folder. | |
| ENGAGEMENT_AUDIENCE | Yes | Audience filter: 'internal' or 'shared'. Unknown values fail closed. | |
| ENGAGEMENT_ALLOW_WRITE | No | Set to 1 to enable the log_document intake write tool. Read-only otherwise. | 0 |
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 |
|---|---|
| job_overviewA | One-screen status of the engagement: node counts by class, gate states, HIGH-severity items, and open decisions. Read-only. |
| get_nodeC | Return a visible node and backlinks, omitting restricted relationship IDs. |
| findA | Keyword search over node ids, labels, and notes. Optional class filter (client, engagement, deliverable, document_slot, gate, open_item, ...). |
| open_itemsB | Every open item in the ontology: open_items, unmet gates, and HIGH-severity nodes. |
| gate_checkC | Report gates and incomplete dependencies, conservatively hiding restricted prerequisites. Cycles and unresolved references are blockers. No result grants human approval. |
| read_docC | Read bounded UTF-8 text by document stem; shared mode lists only shareable documents. |
| run_checkB | Validate graph links and visible approval gates without running any local program. |
| intake_statusA | Which document slots have something logged in the intake ledger, and which are still empty. |
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 8 tools
The core resource/action pairs are mostly understandable, but job_overview, open_items, gate_check, and run_check overlap around gate states, HIGH-severity items, and validation. Descriptions help separate summary vs listing vs validation, but an agent can still reasonably hesitate among several tools for a status or gate query.
All names use lowercase snake_case, which is readable, but the semantic patterns are mixed: verb_noun (get_node, read_doc), noun_phrase (job_overview, open_items, intake_status), and single verb (find). The convention is not chaotic, but it is not predictably consistent.
Eight tools is a well-scoped size for a read-only engagement oversight server. Each tool appears to earn its place across overview, search, node inspection, open items, gates, validation, intake, and document reading.
The surface covers the apparent read-only domain well: status, search, node retrieval, open items, gate validation, intake tracking, and document reading. Minor gaps remain, such as no explicit broad node listing beyond keyword search, but agents can mostly work around this via find and get_node.