MCP Agent Operations
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_AGENT_OPS_SKILL_ROOTS | No | Configure readable skill roots using the operating system path separator between roots. | |
| MCP_AGENT_OPS_DETECTION_REGISTRY | No | Configure the methodology-owned technology registry. |
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
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| claim_statusC | Return primary-root claim state or a structured migration stop without creating absent state. |
| claim_acquireB | Atomically acquire one work item, file domain, or timed resource. Work-item scope uses work_item_id with activity work or update. Named resources require complete timing evidence resolved against PROJECT.yaml. Project-files excludes backlog and supports caller-requested isolation only beneath the primary worktree's canonical .worktrees/ root, with backlog omitted through worktree-specific sparse checkout. Schema-version-2 results preserve the package-owned claim engine's current outcomes, rejection fields, and exit codes. |
| claim_extendA | Atomically add same-domain scope without weakening existing ownership. A work-item claim cannot add operational scope. A named resource extension requires complete timing evidence. Primary-only scope from a linked claim returns SHARED_CHECKOUT_REQUIRED; invalid mixed scope leaves the registry unchanged. |
| claim_extend_deadlineC | Extend one configured resource hard stop with bounded evidence. |
| claim_heartbeatC | Refresh one active claim heartbeat in the repository-global registry. |
| claim_releaseC | Release one exact claim, including a disposition for work-item ownership. |
| claim_resetB | Replace the live registry with an empty claim list under its exact lock. |
| claim_maintain_journalB | Archive complete UTC claim-event days while retaining the configured hot window. |
| claim_reportA | Report canonical contention metrics without creating or migrating absent state. |
| render_hierarchy_htmlA | Render safe self-contained hierarchy HTML and optionally save it. Inline mappings, sequences, JSON, and YAML require no filesystem access. An
explicit source path, custom theme folder, or output folder must be absolute and
resolve beneath |
| create_hierarchy_planA | Create a durable hierarchy JSON plan and its same-named HTML rendering. Source and theme paths must be absolute beneath configured workspace roots. The output folder follows the same boundary and defaults to the authorized server project directory. |
| update_hierarchy_planA | Apply exactly one targeted plan mutation and regenerate its HTML rendering. The plan path must be absolute beneath configured workspace roots. The target is
an exact dotted hierarchy number or an exact unique title. Supply exactly one of
|
| verify_yamlB | Validate exact YAML files, including duplicate keys, with structured diagnostics. |
| verify_markdown_linksB | Verify local Markdown targets and anchors selected by simple root-relative globs. |
| reference_loadC | Load recursive text references aggregated across every matching allowed folder. |
| reference_refreshB | Atomically refresh project and configured user reference scopes. |
| skill_listA | List path-free skill metadata, digests, resources, and shadowing counts. |
| skill_findA | Return the precedence-resolved absolute |
| skill_readB | Read one precedence-resolved skill and optionally append its extension. |
| skill_read_resourceA | Read one supporting skill resource without permitting directory traversal. |
| skill_loadB | Load skills and optionally append independently resolved extensions. |
| skill_resource_loadB | Load several supporting resources in one ordered all-or-nothing operation. |
| skill_refreshA | Atomically refresh project and configured user skill roots. |
| skill_validateB | Validate catalog names or explicit skill paths beneath the working project. |
| detect_technology_skillsC | Detect required technology skills for project scopes using the configured registry. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| skill_catalog_resource | Return the current structured skill catalog as JSON. |
TDQS
Scored across 25 tools
Each tool has a clearly distinct purpose, especially within the claims cluster where verbs like acquire, extend, release, and status differentiate them. No two tools seem to perform the same action, though the many claim-related tools could require careful reading.
The naming convention is consistent within each domain (claim_*, skill_*, render_hierarchy_*, verify_*) but mixes noun_verb (claim_acquire) and verb_noun (create_hierarchy_plan) patterns across the server. This inconsistency could make tool naming less predictable.
With 25 tools, the count is at the high end and feels heavy for an MCP server. The multiple domains justify some breadth, but the set could likely be consolidated without losing clarity.
Claims have strong lifecycle coverage, but other areas have gaps: hierarchy plans have no delete operation, skills only support read/load/validate without creation or removal, and references only load/refresh. Some obvious operations are missing, making the surface incomplete.