Skip to main content
Glama
martinbechard

MCP Agent Operations

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_AGENT_OPS_SKILL_ROOTSNoConfigure readable skill roots using the operating system path separator between roots.
MCP_AGENT_OPS_DETECTION_REGISTRYNoConfigure the methodology-owned technology registry.

Capabilities

Features and capabilities supported by this server

CapabilityDetails
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

NameDescription
claim_statusA

Return the authoritative live claim registry for one Git repository.

claim_acquireB

Atomically acquire one file domain plus optional exclusive resources.

Project-files excludes backlog and supports isolation only beneath the primary worktree's canonical .worktrees/ root, with backlog omitted through worktree-specific sparse checkout. Backlog and all-files are primary-worktree-only. The three broad selectors are mutually exclusive; project-files and all-files require scope_reason. Schema-version-2 results return SHARED_CHECKOUT_ACQUIRED, ISOLATED_CHECKOUT_ACQUIRED, CLAIM_SCOPE_CONFLICT_WAIT_REQUIRED, SHARED_CHECKOUT_REQUIRED, SHARED_CHECKOUT_RELEASE_REQUIRED, ISOLATED_CHECKOUT_SETUP_REQUIRED, DIRTY_CHECKOUT_RECOVERY_AUTHORIZATION_REQUIRED, DIRTY_CHECKOUT_RECOVERY_ACQUIRED, or a structured rejection with the copied claim engine's stable exit code. Renamed outcomes also carry legacy_outcome.

claim_extendA

Atomically add same-domain scope without weakening existing ownership.

Backlog-domain or all-files extension from an isolated claim returns SHARED_CHECKOUT_REQUIRED. Mixed project/backlog extension returns structured INVALID_SCOPE; project-files and all-files require scope_reason.

claim_heartbeatC

Refresh one active claim heartbeat in the repository-global registry.

claim_releaseA

Release a clean committed claim or an explicitly declared no-change claim.

claim_maintain_journalC

Archive complete UTC claim-event days while retaining the configured hot window.

claim_reportA

Report claim contention and lifecycle metrics without mutating the live registry.

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.

skill_listA

List path-free skill metadata, digests, resources, and shadowing counts.

skill_findA

Return the precedence-resolved absolute SKILL.md path for one skill name.

skill_readB

Read one complete precedence-resolved skill without host filesystem paths.

skill_read_resourceA

Read one supporting skill resource without permitting directory traversal.

skill_loadA

Load several complete skills in one ordered all-or-nothing operation.

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

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
skill_catalog_resourceReturn the current structured skill catalog as JSON.

Latest Blog Posts

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/martinbechard/mcp-agent-ops'

If you have feedback or need assistance with the MCP directory API, please join our Discord server