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 the hierarchy roots. A filename without an explicit or configured output folder returns inline HTML without writing a file. |
| create_hierarchy_planA | Create a hierarchy plan as durable files or canonical inline JSON. Source, theme, and output paths must be absolute beneath the hierarchy roots. The
output folder defaults to |
| update_hierarchy_planA | Apply exactly one targeted plan mutation and regenerate its HTML rendering. The plan path must be absolute beneath the hierarchy roots. The target is
an exact dotted hierarchy number or an exact unique title. Supply exactly one of
|
| verify_yamlC | Validate exact YAML files, including duplicate keys, with structured diagnostics. |
| capture_repository_stateA | Capture an opaque process-local checkpoint without changing the repository. |
| verify_markdown_linksB | Verify local Markdown links using explicit or server-derived file selection. |
| 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 26 tools
The tool set is split into reasonably clear sub-domains (claim_*, skill_*, reference_*, verify_*, hierarchy), but several near-pairs invite misselection: skill_read vs skill_load, skill_read_resource vs skill_resource_load, and claim_extend vs claim_extend_deadline differ only in plurality or nuance. The long inline descriptions clarify the distinctions, but an agent must read them carefully to choose correctly.
Most tools use a domain-prefix convention (claim_acquire, skill_list, reference_load, verify_yaml), but the hierarchy and detection tools break it by leading with the verb (create_hierarchy_plan, render_hierarchy_html, detect_technology_skills) and capture_repository_state stands alone. The mixture of prefix-first and verb-first orderings means there is no single predictable pattern, though each name is still readable.
At 26 tools the surface is heavy, and it spans six loosely related sub-domains (claims, skills, references, hierarchy plans, verification, capture) rather than one coherent domain. Many tools are legitimate, but the aggregate exceeds what an agent can hold comfortably and pushes past the 25-tool threshold.
The claim lifecycle is essentially complete (acquire, extend, extend_deadline, heartbeat, release, reset, status, report, journal maintenance), and skills cover list/find/read/load/resources/refresh/validate/detect. Minor gaps remain: hierarchy plans can be created, updated, and rendered but never listed, read back, or deleted, and reference handling lacks a validate counterpart to reference_refresh.