MCP-Server für strukturierte Workflows zur Wettbewerbs- und Marktbeobachtung (Competitive/Market Intelligence) auf Basis der Perplexity Sonar API.
Korrektur (2026-08-26): Eine frühere Version dieser README behauptete, es gäbe nirgendwo einen nativen Perplexity-MCP-Connector. Das war falsch — Perplexity veröffentlicht einen offiziellen MCP-Server (github.com/perplexityai/modelcontextprotocol), einschließlich eines von Perplexity gehosteten Remote-Endpunkts unter https://api.perplexity.ai/mcp, der aus einer in der Cloud geplanten Sitzung ohne eigenes Hosting erreichbar ist. Wenn Sie nur generische Ad-hoc-Suche mit Sonar benötigen, registrieren Sie diesen, anstatt hier etwas zu bauen oder auszuführen.
Was der offizielle Server nicht bietet, ist eine strukturierte, vergleichbare wöchentliche Marktbeobachtungs-Ausgabe: Er stellt generische Such-/Reasoning-Funktionen bereit (Agent API, Search API), aber keinen Kurzbericht über ein Unternehmen mit festen Abschnitten oder einen durch JSON-Schema eingeschränkten Signal-Sweep. Das ist der eigentliche Grund für die Existenz dieses Servers — er ist eine dünne, schmale Schicht aus zwei Workflow-Tools, kein Ersatz für Perplexitys eigenen MCP-Server.
Stellen Sie dies einmal bereit (siehe „Remote-Bereitstellung“ unten) mit PERPLEXITY_API_KEY als Plattform-Secret, und jeder MCP-Client — einschließlich einer in der Cloud geplanten Cowork/Claude-Sitzung — kann es über HTTP aufrufen, ohne jemals die lokale Maschine oder eine Device-Bridge zu berühren. Registrieren Sie es zusätzlich zum offiziellen Perplexity-Server, nicht an seiner Stelle.
perplexity_company_news — strukturierter Unternehmens-Kurzbericht (Unternehmensführung, Führungskräfte, strategische Ereignisse, Finanzlage, Personalbewegungen), feste Abschnittsüberschriften, lookback_days statt Freitext-Datumsbereichen.
perplexity_market_signals — branchenweiter Signal-Sweep (M&A, Finanzierungen, Ernennungen, Umstrukturierungen), serverseitig auf ein JSON-Schema eingeschränkt, sodass das Ergebnis ein echtes Array diskreter Signale ist und kein Markdown, das erneut geparst werden muss. Gibt ein leeres Array zurück (keinen Fehler), wenn für den Zeitraum nichts Datierbares und Verlässliches gefunden wird — das ist ein aussagekräftiges Ergebnis, kein Fehlschlag.
Beide Tools unterstützen response_format: "markdown" | "json" und geben Zitate/Quellen zurück. Für allgemeine Suche verwenden Sie stattdessen Perplexitys offiziellen MCP-Server — siehe die Korrektur oben.
Related MCP server: INDUSS Research Intelligence MCP Server
npm install
cp .env.example .env # then set PERPLEXITY_API_KEY
npm run buildGut zum Testen oder für jeden Workflow, der bereits auf Ihrer eigenen Maschine läuft. Registrieren Sie es in der Konfiguration Ihres MCP-Clients (z. B. der claude_desktop_config.json von Claude Desktop):
{
"mcpServers": {
"perplexity": {
"command": "node",
"args": ["/absolute/path/to/perplexity-mcp-server/dist/index.js"],
"env": { "PERPLEXITY_API_KEY": "pplx-..." }
}
}
}Das bindet die Verfügbarkeit weiterhin daran, dass diese Maschine eingeschaltet ist — es löst nicht das ursprüngliche Problem, dass eine in der Cloud geplante Aufgabe den Schlüssel benötigt. Verwenden Sie dafür die HTTP-Bereitstellung unten.
Führen Sie denselben Code mit TRANSPORT=http auf einem beliebigen Node-fähigen Host aus (ein kleiner VPS, Render, Railway, Fly.io, ein Container bei jedem Cloud-Anbieter). Die einzigen Anforderungen sind: Node 18+, die Möglichkeit, ein Secret als Umgebungsvariable zu setzen, und eine öffentliche HTTPS-URL.
PERPLEXITY_API_KEY=pplx-... TRANSPORT=http PORT=3000 npm startDer Server stellt bereit:
POST /mcp — der MCP-Endpunkt (streamable HTTP, zustandsloses JSON — ein neuer Server+Transport pro Anfrage, sodass nichts zwischen den Aufrufen durchsickert und es ohne geteilten Zustand horizontal skaliert)
GET /health — einfacher Liveness-Check für den Health-Probe Ihrer Hosting-Plattform
Sobald es hinter HTTPS bereitgestellt ist (https://your-host/mcp), registrieren Sie diese URL im Workspace als Remote-MCP-Connector, damit die Perplexity-abhängige geplante Aufgabe ihn direkt erreichen kann, wobei der Schlüssel serverseitig liegt — dasselbe Betriebsmodell, das Pappers bereits verwendet (nativer Connector, kein lokales Secret im Credential-Pfad).
npm run build kompiliert sauber (strenges TypeScript, kein any).
Beide Transports starten ohne Absturz (stdio und HTTP).
GET /health antwortet korrekt.
Der vollständige MCP-Handshake (initialize, tools/list) gibt beide Tools mit korrekten JSON-Schemas, Beschreibungen und Annotationen zurück.
tools/call mit einem ungültigen API-Schlüssel liefert ein sauberes, umsetzbares Ergebnis mit isError: true (401-Hinweis, der auf das Perplexity-Dashboard verweist) — der Server stürzt nicht ab und bleibt danach ansprechbar.
In der Build-Umgebung stand kein echtes PERPLEXITY_API_KEY zur Verfügung, daher wurde ein tatsächlich erfolgreicher Sonar-Aufruf — echte Antwortinhalte, echte Zitate, die per JSON-Schema eingeschränkte market_signals-Antwort, die tatsächlich als gültiges JSON geparst wird — nicht Ende-zu-Ende getestet. Bevor Sie sich in der Produktions-Marktbeobachtungsroutine darauf verlassen, führen Sie jedes der beiden Tools einmal mit einem echten Schlüssel aus (lokal über stdio genügt für diesen Check) und bestätigen Sie, dass die Ausgabe mit den oben dokumentierten Strukturen übereinstimmt.
perplexity_company_news und perplexity_market_signals verwenden standardmäßig beide das sonar-pro-Modell (tiefere Suche, mehr Quellen, höhere Kosten pro Aufruf als sonar), weil der Marktbeobachtungs-Anwendungsfall Vollständigkeit und Zitierqualität über Latenz/Kosten stellt — das ist die bewusste Standardeinstellung für beide Tools dieses Servers, bestätigt am 2026-08-26. Es gibt hier kein perplexity_search-Tool, um für einmalige Abfragen ein günstigeres Modell zu wählen; verwenden Sie dafür den offiziellen MCP-Server von Perplexity (siehe die Korrektur weiter oben in dieser Datei). Prüfen Sie Perplexitys aktuelle Preise pro Modell, bevor Sie dies im wöchentlichen Routinemaßstab über dutzende Unternehmen hinweg ausführen — ein vollständiger Lauf reichert etwa 50–90 Unternehmen plus einen Marktsignal-Sweep an, sodass sich die Grenzkosten von sonar-pro gegenüber sonar schnell summieren.
Get a structured, cited news brief on one company: governance, executives, strategic events, financial situation, and senior HR moves.
This is a workflow tool built on top of Perplexity's Sonar chat/completions API: it fixes the prompt structure and section headings so every call returns a comparable, five-section brief, and maps a plain lookback_days number to Perplexity's recency buckets (there is no native "3 months" filter, so lookback_days=90 is mapped to the nearest bucket, 'month').
Args:
organization (string): Company name, e.g. "Doctolib".
lookback_days (number, 1-365, default 90): how far back to search ("90" = "last 3 months").
language ('fr'|'en'): default 'fr'.
response_format ('markdown'|'json'): default 'markdown'.
Returns: Markdown: five headed sections (Gouvernance/Governance, Dirigeants/Executives, Événements stratégiques/Strategic events, Situation financière/Financial situation, Mouvements RH/Senior HR moves), each stating "Rien à signaler"/"Nothing to report" if empty, followed by numbered Sources. JSON: { "answer": string (same structured text), "citations": string[], "search_results": [...], "organization": string, "lookback_days": number }
Examples:
Use when: "Quelle est l'actualité récente de Nexans ?" -> organization="Nexans"
Use when: weekly veille loop over a list of target companies -> call once per company
Don't use when: you need sector-wide signals across many companies -> use perplexity_market_signals instead.
Error Handling:
Returns "Error: ... Invalid Perplexity API key" if PERPLEXITY_API_KEY is missing/invalid (401).
Returns "Error: ... rate limit exceeded" if too many requests (429).
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | Language of the synthesized answer. | fr |
| organization | Yes | Legal or commercial name of the company to research, e.g. 'Doctolib'. | |
| lookback_days | No | How far back to look for news, in days (default 90 = 'last 3 months'). Mapped internally to Perplexity's nearest recency bucket. | |
| response_format | No | Output format: 'markdown' for human-readable, 'json' for machine-readable. | markdown |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only and non-destructive; the description adds substantial behavioral context: it explains it wraps Perplexity's API, fixes prompt/section structure, maps lookback_days to recency buckets, emits 'Nothing to report' placeholders, and returns specific errors for bad API keys or rate limits. This goes well beyond the annotations and helps predict actual behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is longer than average, but it is organized into clear, labeled sections (Args, Returns, Examples, Error Handling) with no filler. Every section contributes decision-relevant information, and the main purpose is front-loaded in the first sentence.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is a wraper with no output schema, so the description correctly takes on the burden of documenting return values, error behavior, parameter semantics, and usage boundaries. It covers the full range of invocation contexts and likely failure modes.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema description coverage is 100%, the description adds important meaning beyond the schema: it explains that lookback_days is mapped to Perplexity's nearest recency bucket because no native '3 months' filter exists. It also details what each response_format value produces, including the JSON shape and Markdown sections.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Get a structured, cited news brief on one company,' then lists the exact content areas covered. It also names the sibling tool in the alternatives, making differentiation explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit 'Use when' and 'Don't use when' guidance, including an example user query mapped to the organization parameter. It clearly directs agents to perplexity_market_signals for sector-wide signals instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find recent, dated market signals (M&A, funding rounds, executive appointments, restructurings, etc.) relevant to a given professional profile and region, as a structured list.
Unlike a free-text Sonar query, this tool constrains Perplexity's response to a JSON schema server-side, so the result is a real array of discrete signals — not markdown you have to re-parse. It returns an empty list rather than fabricated signals when nothing dated and reliable is found; that empty list is itself a meaningful, actionable result (it means the sweep ran and found nothing this period), not a failure.
Args:
profile (string): Target professional profile, e.g. "CTO groupe / VP Technology / Chief Transformation Officer / Group CIO".
regions (string[], default ["France","Europe","Luxembourg"]): geographic scope.
lookback_days (number, 1-30, default 7): how far back to search.
signal_types (string[], default M&A/levée de fonds/nomination/restructuration): categories.
language ('fr'|'en'): default 'fr'.
response_format ('markdown'|'json'): default 'markdown'.
Returns: Markdown: one numbered section per signal (title, type, date, source, summary), or an explicit "no signal found" statement if the array is empty. JSON: { "signals": [{title,type,date,source_url,summary}], "count": number, "lookback_days": number, "regions": string[] }
Examples:
Use when: weekly sector-wide sweep independent of any specific tracked company
Don't use when: you already know the company and want its own news -> use perplexity_company_news instead.
Error Handling:
Returns "Error: ... Invalid Perplexity API key" if PERPLEXITY_API_KEY is missing/invalid (401).
Returns "Error: ... rate limit exceeded" if too many requests (429).
If Perplexity returns non-JSON content despite the schema constraint, returns "Error: could not parse signals JSON" with the raw answer included so nothing is silently lost.
| Name | Required | Description | Default |
|---|---|---|---|
| profile | Yes | The professional profile signals should be relevant to, e.g. 'CTO groupe / VP Technology / Chief Transformation Officer / Group CIO'. | |
| regions | No | Geographic scope for signals. | |
| language | No | Language of the synthesized answer. | fr |
| signal_types | No | Categories of signal to look for. | |
| lookback_days | No | How far back to look for signals, in days (default 7 = 'this week'). | |
| response_format | No | Output format: 'markdown' for human-readable, 'json' for machine-readable. | markdown |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark readOnlyHInt and non-destructive, and the description adds meaningful behavior beyond that: it returns an empty list rather than fabricated signals, treating that empty result as a valid sweep outcome. It also discloses exact error behaviors for 401, 429, and per-answer parsing failures while preserving raw content, which is highly transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with Args, Returns, Examples, and Error Handling sections. The core purpose and sibling differentiation are front-loaded, and each section contributes actionable information without filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description correctly takes responsibility for explaining both Markdown and JSON return shapes. It also covers error handling, empty-result semantics, and representative use cases, giving an agent everything needed to invoke and interpret the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and each parameter already has a description, so the baseline is 3. The description adds value by specifying the exact Markdown and JSON return structures tied to response_format, and by giving concrete examples for profile, signal_types, and lookback_days. This is a modest but genuine increment over the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Find recent, dated market signals ... relevant to a given professional profile and region, as a structured list.' It lists concrete signal categories and explicitly contrasts itself with a free-text Sonar query and with the sibling tool perplexity_company_news, so an agent can distinguish it without opening the schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides explicit 'Use when' and 'Don't use when' guidance: use for 'weekly sector-wide sweep independent of any specific tracked company' and avoid when you want a specific company's news, routing to perplexity_company_news. This leaves no ambiguity about selection versus the sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0perplexity_company_newsperplexity_market_signalsScored across 2 tools
The two tools have cleanly separated domains: one compiles a structured news brief for a single named company, while the other scans for market-wide signals across profiles and regions. Their descriptions explicitly cross-reference when not to use each, removing ambiguity.
Both tool names follow the same `perplexity_<object>` snake_case pattern and clearly indicate their target: `company_news` vs `market_signals`. No mixed conventions or vague verbs.
At two tools, the surface is on the thin side and borders on feeling minimal for a server named after Perplexity. Each tool does earn its place and covers a distinct workflow, but the count is at the low end of acceptable.
The pair covers the two main read-oriented intelligence workflows: focused company monitoring and broader market sweeps. A general free-text search or ask tool is missing, but the server's stated purpose appears to be these richer structured workflows, so the gap is minor.
Real-time financial news & regulatory intelligence: cited search, fetch, summaries, collections.
Realtime financial context for AI agents: what changed, who is affected, and what to watch next. One suite covering news, events, guidance, filing changes, sentiment, stakeholders, and alerts. Information-efficient responses with evidence for every result. First-class point-in-time safety for backtests. Pairs well with web search and a market-data API. All data is our own.
Primary-source SEC filing intelligence and financial/disclosure reconciliation for AI agents.
Search and monitor source-backed AI agent ecosystem signals, briefings, deltas, and source health.
