Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_MIGRATE_REGISTRYNoPath to a registry root containing models/. By default the repository registry is discovered automatically.

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

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
resolve_modelC

Resolve a registry identifier with optional platform context.

get_model_profileC

Return a validated local registry model profile.

check_model_lifecycleB

Interpret reviewed lifecycle facts at a fixed date without live research.

compare_modelsC

Return explicit same/different/unsupported/unknown comparison states.

recommend_modelsC

Hard-filter and deterministically rank compatible registry models.

scan_applicationB

Scan a local Python application into a normalized coupling inventory.

query_live_pricingC

Opt in to an OpenRouter pricing inquiry; canonical registry facts are unchanged.

estimate_migration_costA

Estimate recurring token cost from checked-in canonical pricing.

analyze_promptC

Conservatively analyze prompt characteristics without inference.

prepare_prompt_migrationB

Prepare a prompt migration specification without rewriting the prompt.

validate_promptC

Statically validate prompt assumptions against target registry facts.

analyze_invocationC

Analyze provider invocation and adjacent tool/output couplings.

prepare_invocation_migrationC

Prepare a target invocation contract without editing application files.

generate_migration_planB

Generate an actionable application-level migration manifest without writing files.

generate_migration_reportC

Generate a human-readable report from the integrated migration workflow.

generate_eval_suiteC

Bind a deterministic evaluation corpus to a migration manifest.

run_migration_evalC

Run source and target with user-owned local provider credentials.

compare_outputsC

Compare one paired source/target evaluation result deterministically.

analyze_regressionsC

Return a structured categorized regression report for an evaluation run.

optimize_migrationB

Return bounded, review-only recommendations from observed regression evidence.

propose_registry_updateB

Plan a registry update from supplied evidence without editing canonical files.

create_migration_research_requestD

Scan locally and bound explicit user-scoped research to missing/stale facts.

validate_research_resultC

Run the deterministic scope/policy gate over one research artifact.

validate_evidence_reviewC

Check that an independent evidence review actually covers the research artifact.

build_research_consensusC

Deterministically combine research and review; agent agreement is not evidence.

build_session_registryB

Finalize a run workspace into an immutable, expiring session overlay.

Research and review artifacts must already exist in the workspace; any stage still needing an agent fails closed instead of doing hidden work.

generate_session_migration_planC

Plan a migration over the canonical registry plus one run's session overlay.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

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/Athenaxlee/llm-migrate'

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