Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
INFOBROKER_CONFIGNoPath to config.json (default: ./config.json)./config.json
INFOBROKER_KB_KEYNoOptional 32-byte key for knowledge base encryption. Alternative to INFOBROKER_KB_PASSPHRASE or kb.encryption.key_file in config.
INFOBROKER_EXA_API_KEYNoAPI key for Exa (keyed provider). Set to enable.
INFOBROKER_SEARXNG_URLNoURL for self-hosted SearXNG server (e.g., http://localhost:8080). Required only if enabling SearXNG.
INFOBROKER_YEP_API_KEYNoAPI key for Yep (keyed provider). Set to enable.
INFOBROKER_CONFIG_LOCALNoOptional path to a user config layer (default: config.local.json)config.local.json
INFOBROKER_BRAVE_API_KEYNoAPI key for Brave Search (keyed provider). Set to enable.
INFOBROKER_KB_PASSPHRASENoOptional passphrase for knowledge base encryption. Alternative to INFOBROKER_KB_KEY or kb.encryption.key_file in config.
INFOBROKER_TAVILY_API_KEYNoAPI key for Tavily (keyed provider). Set to enable.

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
}

Tools

Functions exposed to the LLM to take actions

NameDescription
infobroker_search_webA

Search the web, encyclopedia, academic, and code sources through one interface with automatic provider selection and a fallback chain. Use when you need broad or batched search, query autocomplete (suggest), query expansion (expand), ranked passages from the top pages (deep), or a multi-variant research compile that deep-reads each variant (research), and optional in-process analysis of the returned results (analyze: topics, entities, clusters, timeline). Do NOT use for a URL you already have (use infobroker_fetch_page), for high-stakes claim verification (use infobroker_verify_claims), for stored-report recall (use infobroker_manage_kb search), or for academic citations (use infobroker_get_citations). Caches results in the local knowledge base, enforces per-provider rate limits, and needs no API key for the free providers. task_type forces a dispatch chain (for example academic) when the automatic classification picks the wrong one. fresh: false keeps KB-first sufficiency, fresh: true skips KB recall and searches external providers, and fresh: 'blend' keeps cached KB results alongside fresh external results. collection scopes KB recall to a named collection. audience records who will read the result and is echoed in meta.direction with the executed task type, reading depth, result bound and provider pool. When two task types are equally supported and would reach different providers, the tool returns both candidate requirements with an empty result list (meta.direction.ambiguous) instead of searching, so the caller can re-issue with task_type. include_domains restricts results to or prefers listed domains (include_domains_mode: restrict filters, prefer ranks them ahead), on top of the configured blocklist; the response reports the matched and excluded counts. An array query is searched in parallel and merged, and a failed element is reported in meta.per_query without failing the batch. A measurable attribute (attendance, population, area, elevation, percentage, date) returns a sourced facts entry before prose, with meta.fact_status. Returns a JSON envelope prefixed [OK] or [ERROR] with status, provider, results, and meta.

infobroker_fetch_pageA

Fetch a URL and extract clean content through the configured renderer chain (Jina Reader primary, native-HTTP fallback; Wikipedia, Internet Archive, arXiv, and Stack Exchange alternatives). Use when you have a URL and need readable text, passages ranked against a question, or the page's last-updated date. Do NOT use for topic search (use infobroker_search_web) or cross-source claim verification (use infobroker_verify_claims). question returns passages ranked against it, sized by passage_size and capped by max_passages; crawl bounds the same-origin crawl to config caps; extract adds JSON-LD, OpenGraph, and microdata; renderer pins a single backend, and when it is omitted the configured chain runs with native_fetch as the keyless fallback when Jina is slow, throttled, errors, or serves an anti-bot challenge. max_length truncates the returned text only; a truncated page is written in full to a temp file. Makes external HTTP calls and needs no API key. A fresh knowledge-base copy is returned before an outbound fetch when available. Fetched pages auto-index into the knowledge base unless the content policy flags them (see infobroker_manage_kb): flag mode returns without storage, block mode refuses. Unreachable URLs return an [ERROR] envelope with remediation; when a DOI resolves, a blocked page falls back to Crossref metadata or an open-access copy, then to an Internet Archive snapshot, and reports meta.fallback_kind. Paywalls, access restrictions, and anti-bot blocks return access_blocked; connectivity failures return network_error; a non-http(s) URL returns invalid_input naming the read tool. Success returns an [OK] envelope with status, provider, results, and meta.

infobroker_inspect_providersA

Inspect configured search providers: list their state, run a live health check, or report build and spec identity. Use when searches return empty or slow results and you want provider status, quota, or latency, or when choosing which backend to trust. Do NOT use to search (use infobroker_search_web) or to read a page (use infobroker_fetch_page). Read-only: it never modifies configuration, providers, or stored data. list snapshots provider state (including each provider's derived privacy posture) and status filters it; health runs a live outbound probe against provider (required for the health action; subject to that provider's rate limits, so it can be slow; for a generic_http provider with no health_endpoint the probe is a real search query and may consume provider quota or credits); spec reports build and spec identity plus local state health (config drift, backend capabilities, update status) and session counters. Returns an [OK] or [ERROR] JSON envelope with status, provider, and results.

infobroker_verify_claimsA

Verify one or more contested claims against independent sources and return confidence-scored findings. Use when a claim is high-stakes or contested and you need agreement, contradiction, and gaps surfaced with confidence scores, or when a finished draft needs a claim-by-claim fact-check in one call. Do NOT use for simple lookups or broad search (use infobroker_search_web) or citation formatting (use infobroker_get_citations). The loop recalls prior findings from the knowledge base, then searches providers and writes findings back; max_iterations bounds the refinement passes and per-provider rate limits apply, with one HTTP-call budget shared across a batch. Keyed providers need their configured API key; unkeyed tiers run without credentials. Supply exactly one of query (one claim, or a string the server splits into up to five) or claims (a list of independent claims seeded verbatim); a batch returns one finding per distinct claim in caller order, identical claims are collapsed and report every input index they cover, and a claim with no attributed source is reported unverified rather than dropped. priority routes the pool by intent (speed, quality, privacy, free_only); providers restricts the pool and omitting it uses the full dispatch chain; confidence_threshold sets the bar for confirmation, and findings below it are reported unverified. Each source carries a span locating its supporting sentence and an advisory modality (asserted, reported, speculative) that never changes confidence. Returns an [OK] or [ERROR] envelope listing confirmed, contested, and unverified findings with per-source claims, spans, and confidence scores.

infobroker_manage_kbA

Manage the local knowledge base: search cached content, ingest text or URLs, list/get/delete entries, view stats, read persisted claim records, and manage at-rest encryption. Use when you need to archive a generated report (ingest with source_type 'report' and save_to 'kb'), revisit stored content, or manage encryption keys. Do NOT use for fresh external search (use infobroker_search_web) or to fetch a new page (use infobroker_fetch_page). The delete action is destructive and cannot be undone; a lost encryption key makes the store unrecoverable by design. URL ingest dispatches the fetch chain, so it consumes that chain's quota, rate limits, and configured API keys. Parameter semantics: action selects the operation; query for search, text/url plus title and collection for ingest, source_url for get/delete, and operation with key_file for the encryption sub-actions; source_type and freshness_tier tag an ingest and filter search/list; save_to defaults to 'kb', format to 'markdown', max_results to 8; last_updated is auto-detected from fetched URLs when omitted; receipt attaches a claim-to-source manifest to a report ingest and verify_report rechecks it offline. Responses carry an [OK] or [ERROR] envelope: search/list/get return entries, stats returns counts, delete reports the chunks removed.

infobroker_reload_configA

Re-read the configuration file and apply provider, rate-limit, and knowledge-base changes without restarting; active connections are preserved. Use when you have edited config.json or config.local.json, or when passing patch to change configuration programmatically. Do NOT use to inspect configuration or provider state (use infobroker_inspect_providers). patch merges a partial config into the user layer (config.local.json) as it exists on disk, accepting only an allow-listed set of operational keys (provider enablement, priority, rate limits, timeouts and retries; response shape; the update check) and rejecting transport, credential, safety, and resource-bound keys — edit the file directly for those. It validates and activates the merged result before writing, backs up the exact bytes read, and rolls the layer back if activation fails; a null value removes that key from the layer. migrate true backs up and applies registered user-layer migrations before reloading. The call re-reads the startup configuration source and reports any user-layer schema drift. If the new configuration is invalid, the previous configuration stays active and an error is returned. Returns an [OK] or [ERROR] JSON envelope.

infobroker_get_citationsA

Return academic references for a query as BibTeX citations with title, authors, year, venue, DOI, and URL. Use when scholarly writing needs a reference list. Do NOT use for general web search (use infobroker_search_web) or contested-claim verification (use infobroker_verify_claims). query is a natural-language topic; max_results sets the reference count, and larger values take longer and span more sources. References are gathered from every enabled academic provider, deduplicated by DOI (title when absent), and each provider's status is reported in meta.providers; a zero-result answer names the providers tried. Needs no API key when at least one scholarly source is reachable; if every source fails it returns an [ERROR] envelope with remediation, and queries respect per-provider rate limits. Returns an [OK] or [ERROR] JSON envelope.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.7/5.0

Scored across 7 tools

Disambiguation5/5

Each tool targets a distinct stage of the research pipeline (search, fetch, verify, cite, KB manage, config reload, provider inspect), and the descriptions go further by naming the sibling tool to use instead for near-miss cases. Even the multi-action manage_kb and inspect_providers tools are scoped to clearly different objects (local store vs. provider backends).

Naming Consistency5/5

All seven tools share the infobroker_ prefix and a snake_case verb_noun pattern (search_web, fetch_page, verify_claims, manage_kb, reload_config, get_citations, inspect_providers). No mixed casing or inconsistent verb styles.

Tool Count5/5

Seven tools is tightly scoped for a research/infobroker server; every tool covers an orthogonal concern and no tool is redundant. Multi-action tools consolidate what would otherwise be a much larger surface.

Completeness4/5

The surface covers the full research lifecycle: discovery, retrieval, verification, citation, persistent KB CRUD with encryption, plus operational config and provider health. Minor gaps remain, such as no dedicated batch/async job management or explicit collection administration beyond the action parameters in manage_kb.

Maintenance

ActivityActive
ResponsivenessLimited data