Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PHYSICIST_API_KEYNoOptional Bearer token for authentication. Can also be supplied with the -k or --api-key CLI flag.
PHYSICIST_API_URLNoBase URL of the Physicist REST API. Can also be supplied with the -u or --url CLI flag.http://localhost:3000/api/v1
PHYSICIST_TIMEOUT_MSNoHTTP request timeout in milliseconds. Can also be supplied with the -t or --timeout CLI flag.60000

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
}
prompts
{
  "listChanged": true
}
resources
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
searchB

Unified cross-catalog semantic or keyword search across subatomic particles and quantum states in the Physicist comparative physics manifold.

find_counterpartsA

Find nearest physical counterparts or symmetry analogs to a specified subatomic particle or quantum state using 1024-dimensional pgvector cosine distance.

list_particle_groupsB

List particle groups (taxonomic families, structural sectors, supermultiplets) registered in Physicist with subatomic particle counts.

get_particle_groupA

Retrieve details of a single particle group including its subatomic particles.

create_particle_groupC

Create a new particle group record in the catalog.

update_particle_groupC

Update an existing particle group's name or description.

delete_particle_groupA

Delete a particle group and its cascaded subatomic particles and quantum states.

upsert_particle_groups_batchA

Batch insert or update particle groups matching case-insensitively on name.

populate_particle_groupsC

Trigger LLM discovery to populate major particle groups and families with physics descriptions.

populate_particle_group_subatomic_particlesC

Discover and populate subatomic particles for a specific particle group via LLM generation.

list_subatomic_particlesB

List subatomic particles registered in Physicist with filtering by particle group, themes, embedding status, and search keywords.

get_subatomic_particleB

Retrieve details of a single subatomic particle including its particle group and child quantum states.

create_subatomic_particleC

Create a new subatomic particle record in Physicist.

update_subatomic_particleC

Update an existing subatomic particle's attributes.

delete_subatomic_particleB

Delete a subatomic particle and its cascaded quantum states.

upsert_subatomic_particles_batchA

Batch insert or update subatomic particles under a specific particle group matching on lower(name).

generate_subatomic_particle_embeddingC

Generate or regenerate a 1024-dimensional semantic embedding vector for a single subatomic particle.

populate_subatomic_particle_quantum_statesB

Discover and populate quantum states, eigenmodes, and helicity manifolds for a subatomic particle via LLM analysis.

populate_subatomic_particles_bulkA

Bulk trigger discovery of subatomic particles across one or all particle groups via background job.

list_quantum_statesB

List quantum states and eigenmodes registered in Physicist with filtering by subatomic particle, particle group, themes, and embedding status.

get_quantum_stateC

Retrieve details of a single quantum state including parent subatomic particle and particle group metadata.

create_quantum_stateC

Create a new quantum state or eigenmode under a subatomic particle.

update_quantum_stateC

Update an existing quantum state's attributes.

delete_quantum_stateC

Delete a quantum state from the catalog.

upsert_quantum_states_batchB

Batch insert or update quantum states for a specific subatomic particle matching on lower(name).

generate_quantum_state_embeddingC

Generate or regenerate a 1024-dimensional semantic embedding vector for a quantum state.

populate_quantum_states_bulkC

Bulk trigger discovery of quantum states across all subatomic particles under an optional subatomic particle scope.

compute_clustersB

Compute live connected-components vector clusters for SubatomicParticles or QuantumStates across particle groups without modifying the database.

create_cluster_snapshotB

Compute connected-components clustering and freeze it immediately into an immutable database snapshot.

list_cluster_snapshotsC

List frozen archetype cluster snapshots in Physicist.

get_cluster_snapshotC

Retrieve details of a frozen cluster snapshot including member groups and generated synthesis reports.

delete_cluster_snapshotB

Delete a frozen cluster snapshot along with its cascaded cluster groups and synthesis reports.

list_cluster_groupsB

List all archetype cluster groups belonging to a specific frozen snapshot.

get_cluster_groupB

Retrieve details of a specific archetype cluster group with all member subatomic particles or quantum states.

list_cluster_reportsC

List generated multi-phase comparative particle physics and quantum state manifold synthesis reports.

get_cluster_reportB

Retrieve complete scholarly physics report content, progress percentage, markdown monograph, and intermediate summaries.

create_cluster_reportB

Initiate a 2-Phase Map-Reduce synthesis report on a frozen cluster snapshot.

delete_cluster_reportB

Delete a cluster report and its intermediate summaries.

generate_deep_synthesisC

Upgrade or run a 3-Phase Hierarchical Deep Synthesis report over a cluster snapshot with intermediate batch aggregation.

list_report_summariesB

List all Phase 1 per-cluster analyses belonging to a synthesis report.

get_report_summaryC

Retrieve a single Phase 1 per-cluster scholarly summary.

list_report_sub_reportsB

List all Phase 2 intermediate batch analyses belonging to a detailed synthesis report.

get_report_sub_reportC

Retrieve a single Phase 2 batch analysis.

list_jobsB

List recent asynchronous background jobs (embedding calculations, LLM discoveries, synthesis reports).

get_job_statusB

Check the status, progress, and result of an ActiveJob/Sidekiq background task.

wait_for_jobA

Poll a background job until completion or failure with configurable timeout.

get_platform_statusA

Get overall platform health, catalog entity counts, embedding coverage stats, and active LLM configuration.

get_settingsA

Get embedding completion metrics for SubatomicParticles and QuantumStates, active embedding/LLM parameters, and context window presets.

update_context_windowC

Dynamically update the active LLM context window token size.

trigger_bulk_embeddingsB

Enqueue bulk embedding generation for all SubatomicParticles or QuantumStates.

get_openapi_specA

Retrieve the raw OpenAPI 3.1 specification for the Physicist API.

Prompts

Interactive templates invoked by user choice

NameDescription
comparative_particle_analysisPrompt template for comparing two subatomic particles or quantum states across particle groups using gauge invariants, spin-statistics, and semantic manifold distance.
quantum_cluster_monographPrompt template to draft an academic physics treatise based on Physicist archetype clusters and frozen snapshots.

Resources

Contextual data attached and managed by the client

NameDescription
platform-status
particle-groups-catalog

TDQS

B3/5.0

Scored across 51 tools

Disambiguation3/5

Many tools share the 'populate' verb with subtly different scopes (populate_particle_groups, populate_particle_group_subatomic_particles, populate_subatomic_particles_bulk, populate_subatomic_particle_quantum_states, populate_quantum_states_bulk), and generate_deep_synthesis vs create_cluster_report vs compute_clusters vs create_cluster_snapshot require careful reading to distinguish. Descriptions do disambiguate most cases, but an agent can easily pick the wrong populate/synthesis variant.

Naming Consistency4/5

The dominant pattern is snake_case verb_noun (list_/get_/create_/update_/delete_/upsert_/populate_/generate_), applied consistently across resources. Minor deviations exist — bare 'search', 'find_counterparts', 'compute_clusters', and 'wait_for_job' — where verb style shifts, but overall the convention is predictable.

Tool Count2/5

51 tools is heavy even for a multi-resource domain with particles, quantum states, groups, clustering, reports, jobs, and settings. Several capabilities could be folded into parameters (e.g. consolidating the five populate_* variants or the report summary/sub-report list/get pairs), and the sheer surface raises selection cost for an agent.

Completeness4/5

The surface covers full CRUD plus batch upserts for particle groups, subatomic particles, and quantum states, along with embeddings, clustering, report lifecycle, job polling, and platform settings. Gaps are minor: no job cancellation, no report update/regeneration, and snapshot lifecycle lacks an export/merge operation, but core workflows are covered.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues