Enables searching, retrieving, summarizing, and comparing official central-bank time series, with resource and prompt access for generating reports and evaluating answers against memory-only responses.

Enables Claude Code and Codex to write, update, and retrieve durable long-term memories that survive session boundaries and context compaction. All recall runs locally against a single SQLite file using hybrid BM25, embedding, and recency ranking cut to an explicit token budget, with no cloud dependency.

Enables Claude to answer questions with official Peruvian banking, pension-fund, and insurance statistics, including delinquency, solvency, market share, fees, profitability, and rankings, while citing the bulletin, period, and source spreadsheet for each figure.

Enables on-demand discovery and loading of locally registered skills through read-only MCP tools, respecting explicit-invocation policies and returning skill instructions with paths to scripts, templates, and references.

Enables AI agents to test WCF/SOAP and REST services directly, with WSDL discovery, authenticated calls, and deterministic assertions. Supports YAML multi-step scenarios with variable extraction, JSONPath/JSON Schema checks, and CI runs without spawning PowerShell or curl.

Enables coding agents to check whether a GitHub issue is ready to hand off before starting work, predicting the files and tests the fix will touch from the live checkout and holding back under-specified issues with a single clarifying question.

A read-only MCP server that lets AI agents query a user's own Garmin Connect data via Garmin's official Personal API. It exposes activities, daily wellness metrics, sleep and recovery, and body/profile data as tools for natural-language analysis.

Enables automated, reproducible first-order hydrodynamic analysis through parametric geometry, mesh and static-equilibrium quality gates, and asynchronous solver runs that return six-DOF RAO amplitudes and phases.

Enables AI clients to read Charles Schwab account information over local stdio, including positions, transaction history, and option chains. It is unofficial and read-only, with credentials kept on the local machine.

Enables AI assistants to run local Radiance lighting and daylighting simulations on user-owned models, including annual daylight, compliance metrics, renders, glare analysis and electric lighting studies, with reproducible exported scripts.

Enables offline King James Version Bible lookup, passage retrieval, word and phrase search, deterministic verse-of-the-day access, and book/chapter listing for AI assistants. All tools are read-only and return citable references with structured JSON.

Enables Claude to plan search-and-rescue operations on CalTopo maps by measuring terrain, staging areas, hasty search lines, parking, helicopter landing zones, egress routes, walking-time rings, hospitals, and urban assignments, and by exporting results as GeoJSON draft assignments. It is read-only and returns facts for human decision-making.

Enables MCP clients to identify connected drives, read/write and back up parameters, control speed and positioning, capture oscilloscope data, flash firmware, and run validation workflows through existing Drivesoft communication components.

Enables MCP clients to generate images, videos, and Seedance clips through the PowerTokens official REST API, including model and pricing discovery, cost estimation, asset uploads for first/last-frame references, and automatic polling and downloading of results.

Enables an AI assistant to read raw source text and propose FollowTheMoney records into a hydra archive, checking them against the archive's schema and existing entities, linking rather than duplicating, and storing the text as the cited evidence. Supports drafting, dry runs, saving, read-back verification, image hints and archive creation while leaving uncertain judgments to human review.

Exposes tools that let an agent read a CV, search the Arbeitnow job board for Berlin AI/ML working student roles, score each vacancy against the CV, draft cover letters whose every claim cites CV facts, and queue them for human approval. The same tools can be driven from other MCP clients such as Claude Desktop, with scoring done deterministically in code and limits enforced outside the prompt.

Enables AI coding agents to manage agile boards and notes, including cards, epics, sprints, labels, progress and verification records tied to commits, human-reviewed criteria and decisions, and Area documentation.

Enables agents to download single model weight files from Hugging Face repositories or Civitai model versions directly into allowlisted ComfyUI model folders. Source identifiers, destination categories, and file extensions are validated, and existing files are never overwritten.

Enables AI agents to prepare, launch, monitor, inspect, and recover existing Nextflow workflows through MCP tools, while client-side expert skills guide pipeline-specific input selection, parameters, QC, and troubleshooting.

Exposes agent-facing tools that let a personal AI agent submit each proposed action for an allow, require_approval, or deny verdict against OWASP PAA10 policy rules, plus tools to record provenance-tagged memories, log refusals, read status, and trigger a self-stop. Its decisions are advisory unless paired with the project's gating proxy or hook, which enforce them.

Enables read-only access to generated technical documentation across one or multiple documented repositories, exposing tools to search code and docs, inspect modules and symbols, list gaps, review architecture, and check freshness with file#line citations.

Enables ChatGPT and Claude users to play a turn-based game through an interactive board widget, with the server enforcing rules, validating moves, and tracking game state.

Enables an AI assistant to search open roles at a configured short list of companies through official public Greenhouse, Lever, and Ashby job board APIs, filter matches by career lane, retrieve full job descriptions, and save selected roles to a Notion tracker.

Enables AI agents to read WeChat Official Account articles by fetching mp.weixin.qq.com links from the user's own machine and network and converting them into clean Markdown with title, account, author, and publish-time metadata. Provides both single-article and batch-reading tools (up to 20 URLs) with optional image handling, character limits, and JSON output.