Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
FPF_MCP_SURFACENoSurface level for MCP tools: 'public' (default) or 'full' (expert tools).public
FPF_UPSTREAM_REFNoBranch, tag, or SHA used by spec:download and publish:current.main
FPF_UPSTREAM_REPONoGitHub repo for upstream publication provenance and downloads.FPF
FPF_UPSTREAM_OWNERNoGitHub owner for upstream publication provenance and downloads.ailev
FPF_LOCAL_LLM_MODELNoOptional LM Studio model.google/gemma-4-31b
FPF_RUNTIME_LOG_PATHNoStructured runtime/MCP logs..runtime/logs/fpf-runtime.log
FPF_SPEC_SOURCE_PATHNoLocal path to the spec the runtime reads (must be a filesystem path).published/current/FPF-Spec.md
FPF_AI_TRACE_LOG_PATHNoPer-call LM Studio synthesis traces (JSONL)..runtime/logs/ai-traces.jsonl
FPF_LOCAL_LLM_API_KEYNoLM Studio API token (Developer → Server Settings → Manage Tokens).
FPF_LOCAL_LLM_BASE_URLNoOptional LM Studio endpoint. Omit to stay fully deterministic.http://localhost:1234/v1
FPF_QUERY_DEFAULT_MODENoDefault mode for query_fpf_spec and ask_fpf.verbose
FPF_UPSTREAM_SPEC_PATHNoPath to the spec inside the upstream repo.FPF-Spec.md
FPF_PUBLISH_SOURCE_PATHNoLocal source used by publish:current..fpf-upstream/FPF-Spec.md
FPF_LOCAL_LLM_TIMEOUT_MSNoLM Studio request timeout.20000
FPF_RUNTIME_ARTIFACT_DIRNoWhere compiled artifacts are written..runtime/fpf-index
FPF_RUNTIME_OBSERVABILITY_PATHNoObservability snapshot file..runtime/logs/runtime-observability.json

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

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/venikman/fpf-memory'

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