World Intelligence MCP Server — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow data-provider coverage and attribution as world-intelligence sources change

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Real-time global intelligence across markets, conflict, cyber, climate and public data

What we know

Large MCP server aggregating public APIs across 30+ intelligence domains with cited briefs, geofences, digests, dashboard and optional vector search.

Maintenance / activity evidence

Observed Sep 2, 2026 (UTC)Release 0.10.0 docs

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Activity source · commits ↗Activity source · releases ↗

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Primarily read/query access to public intelligence sources. Writes: Write local reports/vector data.
Authentication not yet verified.
Sensitive access: Research queries, Potential sensitive intelligence interests

Mostly read-oriented public intelligence, but query topics and accumulated research history may be sensitive.

Security source · repository notice ↗Security source · policy file ↗

Full authority, access and evidence limits are available in Review context and Access & risk.

Popularity

651 repository stars

Stars observed Sep 25, 2026.

Preserve any already-reviewed adoption metrics in MCP100. Batch 4 did not refresh package downloads because the package-stats provider had insufficient credits.

All limitations / Review context

Which intelligence sources and query tools remain attributable and maintained?

The bounded assessment reviewed the official README, repository notices, security policy path, and security page for known material public-tracking blockers. No such blocker was identified. This is a public-tracking assessment, not an installation safety certification.

Mostly read-oriented public intelligence, but query topics and accumulated research history may be sensitive.
Primarily read/query access to public intelligence sources.
Queries and fetched public-source data are processed locally; optional vector store persists accumulated intelligence.
Reviewed write actions: Write local reports/vector data
Sensitive access: Research queries, Potential sensitive intelligence interests
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
No independent runtime, installation, or comprehensive security audit was performed.
No installation, runtime, client matrix, or complete tool-contract audit was performed in this review.
Large tool surface and many external public data sources.
Source availability/rate limits can vary.

Original activity observations

2026-09-02T20:53:24Z: Release 0.10.0 docs

Technical identity

github.com/marc-shade/world-intel-mcp

Exact implementation source: https://github.com/marc-shade/world-intel-mcp ↗
Reviewed resource type: MCP Server
Repository identity: marc-shade/world-intel-mcp
Package identity: pypi:world-intel-mcp

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 6, 2026

GitHub repository ↗
marc-shade/world-intel-mcp
Recorded repository material and project history.

Setup · Watchlist

Install & Agents

claude-code

Publisher instructions with a documented client setup path.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Warning

Some tool data arrives from external intelligence feeds; verify source timestamps.
Source-backed ordered steps assembled from publisher README; not claimed to be one verbatim block.
Publisher README shows ~/.claude.json for Claude Code; not native Codex config.toml. WARNING: this snippet is documented in publisher Claude Code JSON context; it is NOT a claim that the same file/path is valid for Claude Desktop, Codex TOML or another host. Publisher-supported parameters assembled into a machine-readable JSON example; placeholders are user-specific and no real credentials are included. Treat as reviewed composed example rather than a verbatim executable test.
uninstall editable pip package only in the installation virtual environment; preserve Qdrant/vector cache and collected data unless explicitly removed.
Distinguish client registration removal from software uninstall, persistent data deletion and provider OAuth/API-key revocation.

Install / connect
Publisher instructions
World Intel MCP is a local Python stdio server with optional dashboard/vector dependencies.
package install · Publisher instructions
git clone https://github.com/marc-shade/world-intel-mcp.git cd world-intel-mcp pip install -e .
Configure / authenticate
MCP100 setup guide
Publisher installs local Python project with pip install -e . and exposes intel status CLI. Some intelligence providers have optional credentials; keyless data feeds and paid feeds are not interchangeable.
Advanced configuration · claude desktop json · MCP100 composed guide
claude desktop json · MCP100 composed guide
{ "mcpServers": { "world-intel-mcp": { "args": [], "command": "world-intel-mcp" } } }
Check connection
Publisher instructions
Use intel status for local caches/circuit breakers and an openly documented read-only source.
read only local inspection · Publisher instructions
intel status
Remove / uninstall / revoke
MCP100 setup guide
Only after uninstalling the editable package whose distribution name matches; first remove relevant MCP client entry. If installed `pip install -e .`, run pip uninstall for actual installed distribution name as shown by `pip list`.
Distinguish client registration removal from software uninstall, persistent data deletion and provider OAuth/API-key revocation.
pip uninstall world-intel-mcp

Official Documentation & Sources

What it does

Large MCP server aggregating public APIs across 30+ intelligence domains with cited briefs, geofences, digests, dashboard and optional vector search.

Capability: Search & Web
Resource type: MCP Server
Industry: Government & Public Sector, Financial Services & Investing, Cybersecurity
Best fit: Real-time global intelligence across markets, conflict, cyber, climate and public data

Representative uses

Query markets/SEC/conflict/military/cyber/climate data
Generate cited situation briefs
Monitor geofences/escalation
Build daily digests

Limitations

Large tool surface and many external public data sources.
Source availability/rate limits can vary.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Not documented in the reviewed sources
Permissions: Primarily read/query access to public intelligence sources.
Data handling: Queries and fetched public-source data are processed locally; optional vector store persists accumulated intelligence.
Cost: free
Risk and cautions: Mostly read-oriented public intelligence, but query topics and accumulated research history may be sensitive.

Access scope and cautions

Write actions: Write local reports/vector data
Sensitive access: Research queries Potential sensitive intelligence interests
Risk level: moderate

FAQ

Based on reviewed evidence as of 2026-10-06. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Query markets/SEC/conflict/military/cyber/climate data; Generate cited situation briefs; Monitor geofences/escalation; Build daily digests.

What setup information is documented?

Recorded installation/entrypoint step: pip install -e .. Recorded transport: stdio. Prerequisites: Python. These are the documented setup details, not a claim that installation or client compatibility was independently tested.

Can it modify data or perform write operations?

Documented write actions include: Write local reports/vector data. Recorded permission boundary: Primarily read/query access to public intelligence sources.

What data-handling boundary should I consider?

Queries and fetched public-source data are processed locally; optional vector store persists accumulated intelligence. Recorded sensitive-access context: Research queries; Potential sensitive intelligence interests.

What limitations and risks should I check before use?

Mostly read-oriented public intelligence, but query topics and accumulated research history may be sensitive. Large tool surface and many external public data sources. Source availability/rate limits can vary. No independent runtime, installation, or comprehensive security audit was performed.

Is this an official MCP?

Marc Shade is listed as Community implementation in MCP100’s current evidence.