Infobroker
Infobroker is an MCP research server that unifies multi-provider search, content extraction, claim verification, citations, and a local knowledge base behind one tool surface.
Search web, encyclopedia, academic, code, news, and structured sources through one interface with automatic provider selection, fallback, and twenty-one zero-config providers out of twenty-six total.
Batch up to five queries, get query suggestions or expansions, rank page passages with deep reads, and attach in-process analysis such as topics, entities, clusters, and timelines.
Fetch any URL as clean Markdown, ask a page a question to get ranked answer passages, crawl same-origin pages, extract structured metadata, detect last-updated dates, and fall back across renderers or archival/paywall alternatives.
Verify contested claims against independent sources with confidence scores, contradictions, gaps, source provenance, hedged-claim attribution, and knowledge-base recall.
Manage a local cached knowledge base: search, ingest, list, get, delete, view stats, archive reports, read claim records, verify reports offline, and manage at-rest encryption keys.
Generate BibTeX references for scholarly queries.
Inspect providers for status, health, quota, latency, privacy posture, build/spec identity, and local state health.
Hot-reload configuration, apply config patches or migrations, and surface operational notices, rate limits, and quota state.
Use bundled client skills to route research into workflow shapes and produce validated finished reports, with a gated analysis loop for high-stakes questions.
Enables web search via the Brave Search API, supporting higher throughput and specialized queries when an API key is configured.
Provides web search results from DuckDuckGo as a zero-config provider, used in unified search across multiple backends.
Offers access to archived web content through a dedicated renderer, enabling source-specific extraction from the Internet Archive.
Enables web search via a self-hosted SearXNG instance, providing advanced search capabilities when an API key is configured.
Provides search across Wikipedia articles and dedicated content extraction from Wikipedia pages via its specific renderer.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Infobroker search web for recent breakthroughs in fusion energy and verify with multiple sources"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Infobroker
One server. Every source. Research that delivers.
Infobroker is a multi-provider MCP server that unifies web search, structured knowledge, academic, archive, and content-extraction APIs behind a single tool surface. Twenty-one zero-config providers ship in the box — search the web, look up facts, fetch articles — with nothing to configure. Five more providers unlock with an API key or self-hosting. A built-in corroboration engine cross-references independent sources to separate established facts from contested claims. Bundled client skills transform raw research into polished writing. Free first. Privacy always.
North Star
Infobroker is the Bothan Spynet as a tool — a decentralized intelligence network that queries independent sources and routes results through a single, impartial interface. It runs the intelligence cycle: direction, collection, processing and exploitation, analysis and production, dissemination. You supply the requirement and receive the report; the server does the work between, and the knowledge base carries the feedback that closes the loop.
Related MCP server: MCP Info Gatherer
Quick Start
npx -y infobrokerThe npm package ships its default configuration. The server resolves it from
the installed package, so no environment variable is required. Your own
overrides live at ~/.config/infobroker/config.local.json, or at a path set
by INFOBROKER_CONFIG_LOCAL.
To run from a clone instead:
cd Infobroker && npm install && npm run startThe configuration below is written for OpenCode. Other MCP clients connect the same way — a local server command plus the instruction and skill paths — but their config keys and file locations differ, so adapt the block to your client's schema.
Add this to your OpenCode config (~/.config/opencode/opencode.json):
{
"instructions": [
"<path-to-Infobroker>/instructions/search-preferences.md"
],
"skills": {
"paths": [
"<path-to-Infobroker>/skills",
"<path-to-opencode-config>/skills"
]
},
"mcp": {
"infobroker": {
"type": "local",
"command": ["node_modules/.bin/tsx", "src/index.ts"],
"cwd": "<path-to-Infobroker>",
"environment": {
"INFOBROKER_CONFIG": "<path-to-Infobroker>/config.json"
}
}
}
}For an npm install, point instructions and skills.paths at
node_modules/infobroker/... and use ["npx", "-y", "infobroker"] as the
command. On Windows, quote paths containing backslashes.
The mcp block starts the server; the instructions and skills blocks
are what activate the bundled client skills. Without them the skills ship
with the package but stay inert.
Most free providers work immediately; CORE needs a free API key. The keyed providers — Exa, Tavily, Yep — unlock higher throughput and specialized search when enabled, and a self-hosted SearXNG instance puts the search path on infrastructure you operate:
export INFOBROKER_EXA_API_KEY="your-key"Requirements: Node.js 24+.
MCP Server
Your research backend. Seven tools, twenty-six providers, one corroboration engine. The complete feature inventory is documented in the feature taxonomy in the spec. Each tool and requirement has exactly one home there, and each area's gate column matches its requirements' declared gates.
Unified Search
"Search for the location of the second Death Star." "Find scholarly papers on hyperspace travel theories." "Search the latest astromech specs and show me the passages that answer: does the R2 unit pre-date the Clone Wars?"
search_web sends one query to every provider that can answer it. Search
across DuckDuckGo, Wikipedia, academic databases, news, code repositories —
or describe your task and the server picks the best source. Common operators
(site:, filetype:, quoted phrases) pass through to engines that support
them, a preferred language is honored where a provider allows it, and anything
the serving provider drops is reported rather than hidden. Pass an array of
queries to batch several searches in one call. Ask for a deep read and it
fetches the top results, then ranks each page's passages against your query,
so you get the specific text that answers the question instead of links. Pass
analyze: true and the same response carries topic terms, entity mentions,
semantic clusters, and a dated timeline derived from those results — computed
in-process, with no extra request. A query that names a measurable attribute —
attendance, population, area, elevation, a percentage, a date — resolves a
sourced facts entry from Wikidata or a Wikipedia infobox/table ahead of the
prose results. include_domains narrows a search to the sources you trust —
restrict returns only those hosts, prefer ranks them ahead without
excluding the rest — on top of the configured blocklist, and the response
reports the matched and excluded counts. When two task types are equally
supported and would reach different providers, the tool offers both instead of
guessing: you get the candidates and an empty result list, then re-issue with
task_type.
Failed providers fall back silently through a configurable chain so you get
results, not error messages. Other search tools lock you to one engine;
Infobroker routes every query to the right provider and keeps going when one
fails. Every tool also returns the same envelope as a machine-readable
object, so programmatic clients read fields instead of parsing text.
Content Extraction
"Fetch the article on the Battle of Yavin and summarize it." "Get the text of that page about the Death Star plans." "Where, in that report, does it mention the reactor core?"
fetch_page hands any URL to the renderer chain, which starts with Jina
Reader and renders it as clean Markdown optimized for LLM consumption. It
falls back to native HTTP when the primary renderer is slow, throttled, or
errors. Wikipedia and Internet Archive have dedicated
renderers for source-specific extraction. Ask a page a question — pass
question to fetch_page and it returns the passages that answer it, each
scored and ranked, instead of the whole document. Fetch several URLs at once
and each result keeps its own renderer, ranked passages, and top score. Pass
raw: true to get the page text directly, without the JSON wrapper. Long
pages are truncated to 50,000 characters by default; set max_length to
change the cap. Set crawl to walk same-origin links from a page: a crawl is
bounded by configurable page-count and depth caps, and the page-count cap
counts outbound attempts, so a page full of dead links cannot multiply
requests.
Built-in web fetchers return raw HTML; Infobroker gives you clean, readable
content from any source — ready for summarization or analysis. Fetch also
reports the page's date when it can determine one, on plain fetches, crawls,
and structured extraction alike, so you know how current your source is; on a
crawl or an extract the date comes from document metadata, so a page dated only
by a response header reports none there. When a page is paywalled, access-restricted, or
bot-blocked, fetch_page reports access_blocked and falls back to Crossref
metadata or an open-access copy for a DOI, and to an Internet Archive
snapshot when no metadata record exists.
Citations
"Give me BibTeX references for papers on hyperdrive field dynamics." "Cite the paper that first described the hyperdrive field equations."
get_citations searches scholarly sources and returns each reference as a formatted
BibTeX entry with its fields — title, authors, year, venue, and URL — ready
to paste into a reference list.
Provider Intelligence
"Which source should I use to research the Death Star's weakness?" "Show me all available sources and their quota status."
The server knows its own capabilities. search_web auto-selects the
best backend for your task, weighing capability, quota, and latency —
or routes by your intent when you ask for privacy, speed, or free-only
sources. When the automatic choice misses, pass task_type to force a
dispatch chain (for example academic), and meta.task_type reports the
chain that served the query. inspect_providers surfaces every configured
source, reports its
derived privacy posture, and drills into a single provider's uptime and error
history; a provider that has served traffic also reports its last result count,
whether the last attempt yielded ok or zero, and the consecutive
zero-result streak, so a silently drifting parser is visible before the fallback
chain is exhausted. The generated skills/infobroker/references/provider-privacy.md
documents query forwarding, retention, account requirements, and resale for
every provider, marking what configuration cannot establish as unknown rather
than assuming privacy. No other search MCP server gives you operational
visibility into every backend.
Multi-Source Verification
"Verify whether the Empire really destroyed Alderaan." "Find the consensus on who fired first — Han or Greedo."
verify_claims runs a multi-pass truth-finding loop: broad
search across your highest-authority providers — search engines,
encyclopedias, and scholarly indexes — then claim extraction,
cross-source reconciliation, and targeted follow-up for gaps, dispatched
in parallel and stopping early once the truth is pinned down. Hand it a draft
and it takes a claim list, returning one finding per distinct claim in your
order — with every input index for a repeated claim — and an explicit
unverified row for a claim nothing supports, rather than dropping it. Claims
corroborated across independent sources score high
confidence, weighted
by each source's authority; every source is bound to the claim it
supports, with a span locating the supporting sentence and the claim's
modality (asserted, reported, speculative) so a hedged source is never
rendered as flat fact. A report that repeats a hedged claim must carry that
attribution in its body. Republished wire copy and mirrors are collapsed into one source
family, so confidence counts origins, not hosts, and a secondary-only
finding is capped rather than overstated. Contradictions are surfaced with
all perspectives. Gaps trigger refined queries that broaden to the rest of
your providers. It also remembers: prior findings in your knowledge base
participate as corroborating sources before it queries the network, but a
finding is marked confirmed only when its confidence clears the threshold and
at least one agreeing source comes from outside your knowledge base. You get a
structured report — confirmed, contested, and unverified findings — with
source provenance, per-source claims and spans, and confidence scores. Every
other search tool returns a list of links; Infobroker finds the truth and
tells you how sure it is.
Knowledge Base
"Search what you already found about the Rebel Alliance fleet." "Ingest this article so it's cached for next time."
Every search, fetch, and corroboration run is cached; manage_kb checks the
cache before external providers, falling back when results aren't fresh or
relevant, and ingests, reports, or removes content. Content is age-scored,
expired on a schedule, and deduplicated by source and meaning. Retrieval runs
locally with a configurable embedding model; your content never leaves the
machine. manage_kb archives reports: ingest with source_type: "report" and
a receipt, and it returns a report_id. Revisit them with manage_kb list/get,
or write them to a local directory. search_web scopes recall to a named
collection, and fresh: "blend" keeps cached results beside fresh ones.
Corroboration results are also kept as claim records, one per finding, linked
to their sources' retrieval times. Cited sources are copied in as retrievable,
hashed snapshots, so a report can be rechecked after the page changes. Deep reading reports a snapshot hash and freshness tier per page;
each snapshot reports its basis (document or snippet) and truncation. An
archived report must carry a receipt, and the receipt is graded: structural
failures plus the share of claims backed by a stored document rather than a
snippet. No stored sources means ungraded, not ungrounded.
preservation.archive: false keeps snapshots and disables Wayback archiving,
which is bounded and overlapped with snapshot storage, so a slow capture never
delays the response.
Read them with manage_kb action=claims, filtered by query or source_url
and capped by max_results (default 8, max 50). The ledger is sealed at rest
when encryption is on.
A watchlist runner records due-topic claim deltas, retains a topic's claims
across a failed or empty result, and advances last_run; cron owns the
schedule. A report can carry a verification receipt: ingest claims, cited
sources, and the Source Register, which the server hashes. verify_report
rechecks it offline and reports
drift when the report or a source changed, unverifiable for an uncached source,
and a digest mismatch for a tampered manifest. The manifest carries report
metadata and a revision chain. monitor-delta --receipt revalidates a baseline
before comparing and marks a receiptless run unverified. The manifest is sealed
at rest, and encryption transitions reseal it.
Research Pipeline
"Research the construction of the Death Star, then draft a summary." "Fact-check these claims about Darth Vader's origin."
Infobroker doesn't stop at search results. Bundled client skills chain its tools into writing pipelines, routing every request through a solved workflow shape and the writing sub-skills until a finished document comes out the other end. Everything lives in the repository — no external paths or separate install. The full pipeline — the six skills, the workflow shapes, and the escalation path — is detailed in the Skills section. Other search MCP servers produce search results; Infobroker produces finished work.
Operational Visibility
"Show server health." "Hot-reload my config without restarting."
Quota counters persist to disk and survive restarts. Rate limits are
enforced per-provider, not globally. Configuration is hot-reloadable
via reload_config — change providers, adjust chains, or tweak
thresholds without dropping connections, or pass a patch to merge a
change into your user layer with a backup. search_web doubles as
DuckDuckGo query autocomplete. inspect_providers reports the server's build
health, request stats, and local state health — configuration drift,
pending migrations, backend capabilities, and update status. When something
needs your attention — configuration drift, a pending migration, or a
provider cooling down — successful tool responses carry a bounded notices
array with the condition and, where one exists, the fix, so a stale user
layer does not stay invisible. Any response carrying retrieved text also
carries a top-level content_trust marker naming that text as untrusted
external content, so an agent reading a page body can tell data from
instructions; the marker is additive and never alters a retrieved body. You always know what your search server is
doing and how much capacity remains. The check-tdqs gate reports each tool's
parameter counts, schema description coverage, invocation cost, and definition
size, and fails when a definition breaks the deterministic TDQS bar.
Skills
The MCP server is one half of the product. The bundled skills are the other. Six client skills ship in the repository and turn raw research into finished work.
The orchestrator skill (infobroker) opens with a classify gate that
maps your request to a workflow shape: research-and-write, fact-check,
deep-dive, competitive evaluation, literature review, monitoring,
red-team, vetting, or gated analysis. Each shape composes the same
primitives — recall from the knowledge base, search, extract, verify,
write, validate, and cite — into its own sequence and ends with a grep-able
completion token. Every report carries a
machine-readable manifest and a graded Source Register; a validation gate
checks its sections, citations, and manifest values before delivery, and a
shared reference fixes one confidence, likelihood, and source-grade scale.
Four writing sub-skills execute the writing phases: summarization
condenses findings before writing, technical-writing drafts reports and
docs, proofreading polishes language, and translation produces
multilingual output.
The writing pipeline requires a client that loads bundled skills; without skill loading, Infobroker provides tool-level research, not a finished report.
Gated analysis is the escalation shape. When a question is high-stakes or
decision-driving, the classify gate routes to the analysis-loop skill —
a disciplined path with confidence-scored findings, source-reliability
grading, and structured analytic techniques chosen by fit and named with a
rationale — rather than the lighter research-and-write route. It shares the
same primitives and Infobroker tools but runs its own gated workflow, so you
get the rigor without leaving the pipeline.
A single instruction file, search-preferences.md, routes your client
toward these tools: the knowledge base first, external providers only
when the cache falls short. Wire it and the skills directory into your
OpenCode config once — the Quick Start section shows the exact snippet —
and every research request follows the pipeline automatically.
Validated reports export as HTML, JSON, or CSV for reading and archiving. Write your own skill into skills/ to add a workflow shape of your own.
The pipeline diagram lives in references/pipeline-map.md and the
workflow-shape definitions in references/workflows.md. Other search MCP
servers return links; Infobroker ships the writers that turn them into
documented answers.
Providers
Twenty-six providers. Twenty-one work with zero configuration.
Provider | Tier | Type | Key Required |
DuckDuckGo | Built-in | Web search | No |
Jina Reader | Free HTTP | Content extraction | No |
Wikipedia | Free HTTP | Encyclopedia | No |
Wiktionary | Free HTTP | Dictionary | No |
Wikidata | Free HTTP | Structured facts | No |
OpenStreetMap | Free HTTP | Geocoding | No |
Internet Archive | Free HTTP | Historical | No |
arXiv | Free HTTP | Academic | No |
Semantic Scholar | Free HTTP | Academic | Optional |
Stack Exchange | Free HTTP | Code Q&A | Optional |
GitHub | Free HTTP | Code search | Optional |
CORE | Free HTTP | Open access | Required (free) |
OpenAlex | Free HTTP | Academic | No |
Europe PMC | Free HTTP | Academic | No |
Crossref | Free HTTP | Academic | No |
Hacker News | Free HTTP | News | No |
GDELT | Free HTTP | News | No |
SEC EDGAR | Free HTTP | Financial filings | No |
World Bank | Free HTTP | Economic data | No |
Marginalia | Built-in | Small web | No |
Mojeek | Built-in | Independent index | No |
Wiby | Built-in | Small web | No |
Exa | Keyed HTTP | Semantic | Yes |
Tavily | Keyed HTTP | Synthesis | Yes |
Yep | Keyed HTTP | Web, Semantic | Yes |
SearXNG | Self-hosted | Self-hosted search backend | Yes (self) |
Built-in providers and most free-HTTP providers are active out of the box;
CORE needs a free API key. Exa, Tavily, and Yep ship disabled; set
"enabled": true for those in your user layer
(~/.config/infobroker/config.local.json by default, or the path in
INFOBROKER_CONFIG_LOCAL), and export the matching key. A
keyed provider whose key is absent is excluded from dispatch, so nothing
changes for a keyless install. Self-hosted providers point at a server you run
yourself:
export INFOBROKER_SEARXNG_URL="http://localhost:8080"Keyed providers also accept an ordered credential pool via
INFOBROKER_<NAME>_API_KEYS (comma-separated). Infobroker rotates to the
next key when one is rejected or rate-limited, and reports per-key
availability through inspect_providers without ever surfacing key
material.
SearXNG is the only shipped self-hosted provider, and it is optional through and through. Nothing in the server requires it, and nothing is bundled or installed on its behalf — SearXNG runs as a container you operate, and Infobroker queries its JSON endpoint like any other backend. Leave it disabled (the default) and you lose nothing: the privacy-critical chain still serves via Mojeek and DuckDuckGo. Enable it to control the search path: the instance you run receives each query first and forwards it to its configured upstream engines, so disable the engines you do not want to reach.
Configuration
Environment variables tune a deployment. INFOBROKER_CONFIG overrides
the shipped default config (resolved from the installed package when unset),
INFOBROKER_CONFIG_LOCAL points at a user config layer,
INFOBROKER_<NAME>_API_KEY supplies a keyed provider's credential, and
INFOBROKER_<NAME>_URL points at a self-hosted provider or an alternate
renderer endpoint (INFOBROKER_JINA_URL for the Jina Reader).
config.json ships with the package and the repository and holds the
defaults: which providers are enabled, their priority in fallback chains,
rate limits, corroboration parameters, and the task-to-provider dispatch
table. Hot-reloadable via reload_config — edit the file and call the tool,
or pass a patch to merge configuration programmatically; changes take
effect without a restart. A patch is merged over your user layer as it exists
on disk when you call the tool, and a null value removes that key — the
supported way to clear a field your layer declares, such as a provider's
auth_env. A field the shipped config.json also declares comes back after
removal, because that declaration is the provider's own requirement; set
auth_optional to true where the provider allows a keyless use.
Your own overrides live in a separate user layer —
~/.config/infobroker/config.local.json by default, or a path you set via
INFOBROKER_CONFIG_LOCAL. An existing config.local.json beside the
resolved config still wins, so clone deployments keep their current layout.
The layer is preserved across updates. Values in the user layer take
precedence over the shipped defaults; anything left out falls back to
config.json.
config.json carries a schema stamp (config_version). If your user layer
was written for an older schema, or holds a key the current schema no longer
recognizes, the server reports the drift at startup and in every
reload_config response without changing your file. Apply the registered
migrations on demand by calling reload_config with migrate true: the
server first copies your layer to a timestamped *.bak-* file, then updates
it atomically, leaving anything it does not recognize untouched. Set
state.auto_migrate_config to true to apply those migrations automatically at
startup after the merged result validates; the same backup is written first.
If a user layer is invalid, the server starts on shipped defaults, leaves the
file untouched, and reports the error instead of refusing to start.
Provider entries are strict: a key outside the provider schema — for example
result_path where the schema expects results_path — makes the whole user
layer invalid instead of being ignored, so a single typo can suppress every
override in the file. The server reports the offending key and the invalid
value, and the fix belongs in config.local.json; a key the current schema no
longer recognizes is reported as drift rather than silently dropped.
state.update_check (off by default) enables an update-availability check
against the published npm package. When enabled, the check runs in the
background, caches its result for a day, and never downloads or applies an
update. The result appears in inspect_providers action spec and, when a
newer release exists, as a notice.
The knowledge base ships empty. Retrieval runs on a configurable in-process
embedding model selected by kb.embedding_model. By default, the store
writes to a user-scoped path (~/.local/share/infobroker/knowledge-base)
outside the repository, so the content you research and cache stays on your
machine and is never committed. Each deployed instance accumulates its own
store. A legacy vector-store.json store is migrated automatically on first
open and preserved as vector-store.json.migrated-<timestamp>; when encryption
is enabled the plaintext archive is removed instead. There is no legacy backend
to roll back to: recover with a key backup or rekey.
Knowledge base encryption
Research reports and cached pages can be sensitive, and the knowledge
base stores them in a SQLite database (plus -wal/-shm sidecars) in your
home directory. Enable optional
at-rest encryption by adding a kb.encryption block and supplying a key:
{
"kb": {
"encryption": { "enabled": true, "key_file": "~/.config/infobroker/kb.key" }
}
}The key file (plain, 0600) is the most reliable source across MCP clients
and operating systems; INFOBROKER_KB_KEY (a 32-byte key) or
INFOBROKER_KB_PASSPHRASE (a passphrase) also work. Generate a key with
openssl rand -base64 32. Encryption protects the store and disk-saved
reports from anyone who obtains the files without the key — device theft,
backup or cloud-sync leaks, other local accounts. It does not protect
against a malicious MCP client on the same machine, or malware, which
full-disk encryption covers.
Two rules keep this safe. First, encryption is your opt-in: if the key is missing or wrong, the knowledge base locks and reports an error rather than touching your data — so back up the key (a forgotten key or passphrase means the store is unrecoverable by design). Second, the server never writes a partial file: every save is atomic, and an unrecognized or newer store format is never overwritten.
The manage_kb tool's encryption action is the day-to-day surface for this
journey, and it never echoes secret material — generate_key and backup
return file paths, and rekey reads a key file rather than a raw key.
generate_key refuses a key-file path that already exists, so it can never
overwrite the only copy of a key.
Enable by generating a key, backing it up, adding the kb.encryption
block, and reloading; the store is encrypted in place immediately.
Disable by removing the block and reloading; the store is decrypted to
plaintext immediately (keep the key available during the transition so the
server can read the store to decrypt it). Recover a locked store with
status to see the state, verify to confirm a candidate key before
committing it, backup to restore a copy of your key file, and rekey to
move to a new key without losing content. After re-keying, point
kb.encryption.key_file at the new key, reload, then run verify again to
confirm the new key opens the store.
infobroker_manage_kb action=encryption operation=generate_key key_file=~/.local/share/infobroker/keys/kb.key
infobroker_manage_kb action=encryption operation=backup key_file=~/.local/share/infobroker/keys/kb.key.bak
infobroker_reload_configTool-surface key operations (generate_key, backup, rekey's target)
are confined to the keys directory: kb.keys_dir when configured, else the
keys sibling of the knowledge base storage path
(~/.local/share/infobroker/keys by default). A path outside that
directory is refused. The kb.encryption.key_file configuration value is
operator-owned and not subject to the confinement.
Add the kb.encryption block to config.local.json before reloading to
enable, or remove it before reloading to disable. When the store is locked,
status, verify, and rekey remain reachable so you can recover without
first unlocking.
Content policy
Infobroker reads the open web and caches what it retrieves, so retrieved
content is assessed against a configurable policy before it is stored (and,
in the strictest mode, before it is returned). The policy flags content
that matches heuristic categories — prompt-injection instructions,
credential phishing, malware/exploit material, and adult content — and can
consult an external assessment service when one is configured. It is on by
default in flag mode: flagged content is still returned to you for
legitimate research, but it is never written to the knowledge base, and
every flag is recorded in the audit trail.
{
"content_policy": {
"mode": "flag",
"threshold": 0.2,
"patterns": { "prompt_injection": ["ignore previous instructions"] }
}
}Modes: off disables assessment; flag (default) returns but never stores
flagged content; block refuses flagged content to the caller. threshold
tunes sensitivity (0–1, default 0.2 — a single match flags). patterns
extend or override the built-in categories per category name. external_url_env
names an environment variable holding the URL of an external assessor, and
external_api_key_env optionally names one holding its bearer key; when the
external service is unreachable the built-in assessment applies.
Security-relevant events — refused network targets, policy flags, config
reloads, encryption transitions, key operations, and quota exhaustion — are
appended to an owner-only audit log at output.audit_log_path (default
~/.local/share/infobroker/audit.log). Per-provider privacy posture is
generated from config.json into
skills/infobroker/references/provider-privacy.md, including whether the
declared credential makes an account necessary; the gate fails when that
document drifts from configuration.
Operational records are separate: every tool call and outbound provider
request logs its name, status, and elapsed time, never the query, URL, or
content. A multi-query search or a verify_claims batch writes one record
per call plus one per provider request, so a batch multiplies the volume;
output.call_log_max_bytes (default 2 MB) bounds the file before rotation.
Set output.call_log to "stderr" (the default), "file", or
"off"; the file sink is owner-only and rotates at
output.call_log_max_bytes. inspect_providers action=spec reports the
session summary, and a successful response carries a provider_cooldown
notice while a provider is held off after a rate limit.
Bring your own endpoint
Any HTTP search endpoint can become an Infobroker provider without
touching the source tree. Declare it in config.local.json as a
generic_http provider, then append it to a dispatch chain: dispatch_append
adds the slug after the shipped providers instead of replacing the chain.
{
"providers": {
"my_search": {
"tier": "generic_http",
"capabilities": ["web_search"],
"enabled": true,
"priority": 20,
"endpoint": "https://api.example.com/search",
"query_param": "q",
"results_path": "data.items",
"health_endpoint": "https://api.example.com/health",
"auth_env": "INFOBROKER_MYSEARCH_API_KEY",
"field_map": { "title": "name", "url": "link", "snippet": "summary" }
}
},
"dispatch_append": { "general_web": ["my_search"] }
}The server GETs endpoint?query_param=<query>, walks results_path
(dot-separated into the response JSON), and maps each result to the
common shape using field_map. field_map values are dot paths; besides
title, url, snippet, published_date, source_type, and
original_source, it accepts the scholarly keys authors (a string or
array), doi, venue, abstract, and citation_count. Relative result
URLs resolve against the endpoint.
Set auth_env to an environment variable name to send its value as
Authorization: Bearer …; the key never appears in configuration. For an API
that expects a different header or no scheme, set auth_header (default
Authorization) and auth_scheme (default Bearer; set "" to send the raw
key). For example, {"auth_header": "X-API-Key", "auth_scheme": ""} sends the
key alone in X-API-Key. Set
health_endpoint to a query-free URL so inspect_providers health does
not spend a real search against a metered API — without it the probe is a
search query. A generic provider's capabilities must be web_search or a
search task type such as academic; suggest and content_fetch are not
implemented by the shared generic backend. A slug that matches a built-in
provider is rejected. Add the entry to config.local.json and call
reload_config to use it immediately.
priority routes the verify_claims pool by intent without leaving the
provider list: privacy restricts it to providers that do not forward queries
to third parties, quality orders it by configured provider priority, speed
orders it by recent response latency with an unmeasured provider placed after
the measured ones, and free_only drops the keyed and self-hosted tiers. A
list that satisfies no intent is used unchanged. It does not reorder
search_web, which follows dispatch-chain order.
Per-provider status and provenance
Two optional keys tune per-provider behavior in config.json:
degraded_latency_ms— a provider whose recent average latency exceeds this many milliseconds is reporteddegradedby theinspect_providershealth action, even while reachable. A globaloutput.degraded_latency_msacts as the fallback when a provider omits its own.resells— settrueon aggregator/reseller backends (search engines that surface other publishers' pages, like DuckDuckGo or SearXNG). The server reports each result'soriginal_sourcewhere the backing API exposes one (e.g. Yep'ssourcefield); first-party sources (Wikipedia, arXiv) leave it empty because the page is the origin.
Source quality and blocklisting
Search results are ordered by relevance, then adjusted by a configurable
source-quality weight. Primary sources (default .gov, .mil, .edu, and
.int) and domains marked trusted rank higher; domains marked low-quality
rank lower. The default weight is small enough that relevance stays
dominant. A blocklist removes a host and its subdomains before ordering and
reports the count in meta.blocked_count; a *. pattern matches subdomains
only. The blocklist applies to search_web results, including a
knowledge-base recall used to answer a search, and does not apply to
fetch_page or verify_claims.
{
"source_quality": {
"enabled": true,
"weight": 0.15,
"primary_source_suffixes": [".gov", ".edu"],
"trusted_domains": ["nature.com"],
"low_quality_domains": ["contentfarm.example"],
"blocklist": ["spam.example", "*.tracker.example"]
}
}Set weight to 0 to keep pure semantic ordering, or enabled to false
to disable both ranking and blocklisting.
Hedged fallback
search_web and fetch_page fall back with a hedge instead of waiting
out a slow provider's full timeout: the primary (first-choice) provider
runs alone for a latency-derived window, then the remaining providers
race and the first result wins. The common path uses one provider call;
the hedge fires only when the primary is slow or failing. fetch_page
additionally prefers the primary renderer in a short grace window so a
marginally slow jina is not displaced by a lower-quality native_fetch.
A renderer whose content is an anti-bot challenge page (a CAPTCHA or
verification interstitial rather than the target page) is treated as a
failed render, so fetch_page falls through to the next renderer instead
of serving the challenge as content. When a fetch_page renderer race
settles, the losing renderer is cancelled, so it makes no further request
and spends no quota.
Tune the window with output.hedge_enabled, hedge_min_delay_ms,
hedge_max_delay_ms, and hedge_grace_ms; set hedge_enabled to
false for the sequential chain. A provider that returns a rate-limit
or anti-bot response is held in a per-provider cooldown (output.rate_limit_cooldown_ms)
so a burst of requests stops re-hammering it, and when a non-general_web
chain exhausts, the server retries the general_web chain before failing.
How It Compares
Tool name | What you're used to | How Infobroker differs |
Built-in | One search engine, one fetch mode, no configuration, no visibility into what backend is used | Twenty-one zero-config providers with a unified tool surface. Choose the right source for each task. Fall back automatically on failure. See every provider's status and quota. |
Raw API calls | Manual HTTP requests, per-provider auth, per-provider response parsing, no fallback, no quota tracking | One interface for every provider. API keys configured once. Results normalized to a common shape. Rate limits and quota tracked automatically. |
Dedicated search APIs | Pay-per-query, vendor lock-in, opaque routing | Free-first design. DuckDuckGo, Wikipedia, and nineteen other providers work with zero configuration. Upgrade paths for Exa, Tavily, and Yep. A self-hosted SearXNG to keep the front door on your own machine. |
Other search MCP servers | Single-provider focus, no fallback, no corroboration, no writing pipeline | Multi-provider with automatic fallback. Corroboration engine cross-references independent sources. Bundled writing skills transform research into finished documents. |
AI with built-in search | The model picks the search engine, serves stale cache, no reproducibility | You control the provider chain. Queries are reproducible. Fallback behavior is visible. The corroboration engine verifies facts across independent sources. |
Every other search MCP server asks you to pick a provider and trust it. Infobroker gives you a fleet — and picks the right one for each task. When a provider fails, the next one takes over without you noticing. When a claim matters, the corroboration engine finds agreement, contradiction, and gaps. The bundled skills close the loop from raw research to finished writing. One server. Every source. Research that delivers.
Last updated: 2026-11-16.
Contribute
Node.js 24+.
node --version. Get it at nodejs.org.npm install && npm run typecheckBundle your own skill in
skills/to extend the research pipeline.Validate README structure:
npm run validate-readmeVersioning: CalVer (
YYYY.M.D, no leading zeros).npm run version-bumpstamps today's date into the package, server manifest, and version stamps so the package, tag, and npm-published version all name the same release; update the spec stamp and README citation alongside it. Pre-commit hooks verify consistency.npm run pushchecks, tags, and pushes.MCP protocol: modelcontextprotocol.io
Providers: DuckDuckGo · Jina Reader · Wikipedia API
Canonical origin: git.gay/flukeatzerocool/Infobroker. This GitHub repository is a read-only mirror.
License
MIT. Free to use, modify, and redistribute. The bundled client skills and instruction files ship under the same license, so the full research pipeline — server, skills, and documentation — is freely reusable in commercial and open-source work alike. Third-party providers remain subject to their own terms and API keys.
Spec
The server is built from a single source specification, infobroker.md
(v2026.11.16), which defines every requirement and the gates that verify it.
Each requirement traces to an implementation file, and npm run check
reconciles the code, the spec, and this README so what is documented is what
the server actually delivers. The routing gate resolves every cited tool and
operation against the live schema, and requires each registered tool to be
cited at least once.
Available Tools
7 toolsinfobroker_fetch_pageFetch Page ContentAIdempotent
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.
Inputs: url (required), raw, crawl, extract, +6 more. Returns: meta, error, status, notices, +2 more
infobroker_get_citationsGet CitationsARead-onlyIdempotent
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.
Inputs: query (required), max_results. Returns: meta, error, status, notices, +2 more
infobroker_inspect_providersInspect ProvidersARead-onlyIdempotent
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.
Inputs: action (required), status, provider. Returns: meta, error, status, notices, +2 more
infobroker_manage_kbKnowledge BaseADestructive
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.
Inputs: action (required), url, text, query, +12 more. Returns: meta, error, status, notices, +2 more
infobroker_reload_configReload ConfigurationADestructiveIdempotent
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.
Inputs: patch, migrate. Returns: meta, error, status, notices, +2 more
infobroker_search_webWeb SearchARead-onlyIdempotent
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.
Inputs: query (required), deep, page, fresh, +17 more. Returns: meta, error, status, notices, +2 more
infobroker_verify_claimsVerify 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.
Inputs: query, claims, priority, providers, +2 more. Returns: meta, error, status, notices, +2 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
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).
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.
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.
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
Related MCP Connectors
One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
Live AI-native web search with citations. One tool for every MCP client. Flat per-request pricing.
Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.
Free web search for AI agents. No API key required. Hosted MCP in active development.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceZero-auth multi-source research MCP server that enables web search, reading URLs, PDFs, GitHub repos, and querying Hacker News, Stack Overflow, Semantic Scholar, and YouTube transcripts without API keys.58 PyPI12Apache 2.0
- FlicenseAqualityDmaintenanceEnables searching and gathering information from multiple online sources (web, Twitter/X, Telegram, GitHub, Hugging Face, arXiv) through a unified MCP interface.12-
- AlicenseNot gradedqualityFmaintenanceMCP server enabling local-first web search, fetch, extract, and caching with citeable excerpts, no API key required. Supports research workflows for agents and apps.96 npm1MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to perform unified web research through a single MCP server, including search, page fetching, recursive crawling, document parsing, YouTube transcript extraction, and deep multi-query research.3-