Skip to main content
Glama
Repository Manager

Repository Manager

Repository Ingest Repositories

repository_ingest_repositories

Ingests GitLab or GitHub repositories into an epistemic graph as typed GitRepository nodes with clone URL, web URL, and default branch provenance for knowledge graph use.

Instructions

Natively ingest git repositories into epistemic-graph as typed :GitRepository nodes.

Enumerates repositories across a GitLab instance / GitHub org via the real VCS enumerator and pushes them (typed :GitRepository nodes with vcs/clone_url/web_url/ default_branch provenance) into the knowledge graph via the fast engine client. Best-effort: returns {"ingested": None} when no engine is reachable. CONCEPT:MERISTEM-KG.ingest.enterprise-source-extractor.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "repository_ingest_repositories"
  }
}

Input Schema

NameRequiredDescriptionDefault
vcsNoWhich VCS to enumerate: 'gitlab' or 'github'.gitlab
scopesNoComma-separated GitLab groups / GitHub orgs to enumerate. Omit for the whole instance / the authenticated user.
max_reposNoOptional cap on the number of repositories enumerated + ingested.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.5.1

TDQS

B3.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden, and it does disclose the best-effort failure mode ('returns {"ingested": None} when no engine is reachable') plus the fact that it mutates the graph. It says nothing about authentication/token requirements, idempotency or duplicate-node handling on re-ingest, or rate limiting on large instances — meaningful gaps for a write operation against an external VCS.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence is front-loaded and useful, but the prose is padded with jargon ('via the fast engine client', 'real VCS enumerator') and ends with an opaque tag 'CONCEPT:MERISTEM-KG.ingest.enterprise-source-extractor' that conveys nothing to an agent selecting a tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter, all-optional tool with an output schema and full schema coverage, the description covers purpose, mechanism, and the degraded-mode return value. The remaining hole is operational: no guidance on required credentials or on what happens to pre-existing nodes on repeated ingestion.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all three parameters (vcs, scopes, max_repos) are already documented, including scope omission semantics. The description adds no per-parameter meaning beyond mentioning the provenance fields (clone_url/web_url/default_branch) that get stored, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('ingest git repositories into epistemic-graph as typed :GitRepository nodes') and explains the mechanism (enumerate via VCS, push via engine client). It implicitly distinguishes itself from enumeration-only siblings such as rm_git_enumerate by stating it also writes to the graph, though it never names an alternative tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the agent can infer this is the tool that populates the knowledge graph with repository nodes. There is no explicit when-to-use/when-not statement and no pointer to rm_git_enumerate or the repository_manager discovery tools as alternatives for read-only enumeration.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools