pod
Other formats agents might prefer:
markdownjsonllms.txt

Agent? You probably want markdown or json, or Pod over MCP.

MCP Servers with a search_files tool

Every MCP server Pod knows of that exposes a search_files tool.

8 servers, ordered by decision readiness and adoption — GitHub stars and npm downloads where available, then reported issue volume. None have been dialled by Pod yet, so every tool list here is publisher-reported and unverified.

agent-wiki

agent-wiki gives your team one shared source of project memory that everyone's AI assistant can read, search, and update. Create a workspace for your agency or consultancy, then a focused wiki for each client or project — decisions, plans, brand and voice guides, meeting notes, and open questions live in clean files instead of one person's chat history.

Connect Claude once and every project you can access comes with it. Ask for a brief and your assistant pulls the latest context; finish a call and it writes the decisions back to the right file. The next teammate — or the next chat — starts with the current picture instead of an archaeology dig through Slack and old threads.

Built for small agency, consulting, and campaign teams where context changes fast and lives in too many places:

  • One workspace per team, one wiki per client or project.
  • Invite teammates with a link, with owner, admin, and member roles.
  • Wikis are private by default and can be restricted to specific people.
  • Every read and write is logged, with full version history and one-click revert.
  • Sign in with Google; revoke any assistant's access anytime.

agent-wiki works with Claude and any other MCP-connected assistant, so your team is never tied to one tool. And because every page is plain markdown, you can export a whole wiki as .md files that open in any editor — no lock-in, ever.

Start free with one wiki, and upgrade when it becomes part of how the team works.

1 GitHub stars · 9 tools reported — Publisher-reported; not verified by Pod.

Deskfirst

Deskfirst turns scattered files and email threads into a single branded portal you share with a customer. Agencies, consultants, freelancers, and sales teams use it for proposals, onboarding, project handoffs, and ongoing account work — anywhere someone needs one link instead of ten attachments.

With this connector, Claude can create a portal for a new customer or project, organize files and folders inside it, apply your branding, and generate a share link or invite people directly. Start from a reusable template or your content library so every portal opens fully populated.

Claude can also build and maintain Mutual Action Plans: create sections and tasks, assign owners and due dates, attach files, and post comments as work progresses.

The read side is where it earns its place day to day. Ask which customers visited this week, which files they opened and for how long, or which projects have gone quiet — Deskfirst surfaces engagement signals per file and per person, and rolls them up across accounts and team members.

Typical uses: stand up a customer portal the moment a project or deal starts, prep for a call by asking what they've actually been reading, keep an action plan current without switching tabs, and spot stalled work before it surprises you.

65 tools reported — Publisher-reported; not verified by Pod.

Google Drive

Connect Google Drive to Claude to search through your documents, read file contents, upload new files, and analyze your data. Claude can find specific documents even when you don't remember the exact name, read and analyze the content of Google Docs, Sheets, Slides, and PDFs, and upload files directly to your Drive. Useful for finding project notes, extracting data from spreadsheets, preparing meeting materials, or organizing files scattered across your Drive.

11 tools reported — Publisher-reported; not verified by Pod.

Optilogic

Make faster, better tactical decisions within the supply chain you have today and design the supply chain you need for tomorrow. Optilogic connects Claude to a platform that does both. Work with a live digital twin of your current supply chain powered by agentic AI that combines mathematical optimization, simulation, and demand modeling to support decisions across the full horizon, from day-to-day operational response to long-term network, transportation, inventory, and production strategies.

  • Run what-if scenario analysis on network design and sourcing models
  • Analyze demand at the SKU and location level, and trace how it's served across your network
  • Answer strategic and tactical routing questions to drive cost savings and service level improvements
  • Place safety stock across your full network and see what it costs to hit a given service level
  • Score risk across your network: single-source dependencies, demand/facility/supplier concentration, geographic exposure, capacity, and transport-time risk, so you know where to focus before a disruption
  • Model the impact of tariff scenarios
  • Design and compare network strategy across sourcing, manufacturing, distribution, and nearshoring scenarios
  • Stress-test a plan against real-world variability such as demand swings, delayed lead times, and capacity shocks
  • Compare multiple scenarios, sensitivity analysis at-scale, with output and critical insights auto-generated
  • Translate optimization model outputs into decision-ready formats for planners, finance, and executives

Best for: S&OP/IBP leaders, network design teams, transportation teams, supply chain modelers and analysts, operational planners as well as executives who want a straight answer to a "what if" question without needing modeling expertise.

Requires a free or paid Optilogic account. You will be redirected to Optilogic to sign in and authorize access. Your data and models stay secure and isolated in your own account.

37 tools reported — Publisher-reported; not verified by Pod.

Rockhopper

Rockhopper - spreadsheet audit, approvals, and AI-agent governance for Excel & Google Sheets

Rockhopper tracks exactly who - human or AI agent - changed what in a spreadsheet, and adds review/approval workflows on top.

Use it for:

Attribution & history - see which version of a file had AI-made edits vs. human edits; pull cell-level or metric-level change history across versions; surface uncommitted ("unattributed") changes currently sitting in a file.

Versions - list version history for a file, or commit current changes as a new version. Reviews & approvals - create, approve, or cancel a review request for a specific version, so changes go through sign-off before they're final.

Comments - read, add, reply to, and resolve comments and discussion threads on a file, including the latest conversation tied to a specific file.

File management - search enrolled files by name, comment text, or version notes; rename a file.

Trigger this when the user asks who changed a spreadsheet, whether an edit was made by AI or a person, wants to compare periods/versions, needs to approve or request approval for a file, wants to see comments or discussion on a spreadsheet, or names Rockhopper directly. Only works on files already enrolled in the user's Rockhopper workspace (Microsoft Excel or Google Sheets) - it doesn't edit cell data or formulas directly.

16 tools reported — Publisher-reported; not verified by Pod.

ShareWatch

ShareWatch lets Claude create, read, and edit Google Docs, Sheets, and Slides without seeing the rest of your Drive.

Most Drive integrations ask for access to everything. ShareWatch uses Google's drive.file scope instead, so Claude can only reach files that someone has shared through the ShareWatch picker, plus files it creates itself. Google treats everything else as if it doesn't exist and never returns it to the connector.

Once a file is shared, Claude can draft and format Docs with real headings, lists, and links, build and update multi-tab Sheets, create and revise Slides presentations, convert uploaded files to Google formats, and organize, search, and move files within the folders you've opened up.

For individuals, control is one click in each direction. Share a file from the picker, or block it again whenever you want. New files Claude creates go to a default folder you pick.

For organizations, ShareWatch makes AI file access something you can govern and audit. Admins can block any file or folder with a recorded reason. Blocked requests return an audit reference that the user can hand to their admin, so exceptions go through a process instead of a workaround. Access attempts are written to an audit log that admins can review. Business plans add SSO, DLP protections that keep sensitive content from leaving your workspace, and SIEM integration that streams access events to Splunk, with support for other platforms available on request. And since the connector never holds broad Drive permissions, a security review covers one narrow grant rather than tenant-wide Drive access, which makes ShareWatch far easier to approve for teams rolling out Claude under compliance requirements.

ShareWatch works the same way for one person drafting reports and for a company putting Claude to work across Workspace. Claude gets enough access to be useful, and you decide exactly how much that is.

25 tools reported — Publisher-reported; not verified by Pod.

UseMyContext.ai

UseMyContext is context you write yourself - your role, projects, preferences, and files - and approve every change to. Claude reads it on demand, so you never re-introduce yourself.

The same context also connects to ChatGPT, Gemini, and Perplexity - one profile across every AI subscription you have, not locked in one of them.

Connect once and Claude can:

  • Read your profile: a compact summary of who you are, built only from facts you have accepted.
  • Answer from your own files: cited passages from your documents, and exact counts and totals from your spreadsheets - grounded answers, not guesses.
  • Suggest updates as it learns about you, saved as pending items for your review. Nothing is written without your approval.
  • Read contexts others have deliberately shared with you.

The one place on the web where you're in control. As a human. You write what goes in, you approve everything an AI proposes to remember, and you can revoke access in one click. Our public servers cannot read your file content. One account, multiple projects, each with its own profile and files.

Free to start, and you don't need anything prepared: connect with an empty account and Claude interviews you right here in the chat to build your first profile. In Claude Code, npx usemycontext pull loads your context at the start of every session. Premium adds more projects and storage; Team adds a shared team context.

0 GitHub stars · 13 tools reported — Publisher-reported; not verified by Pod.

Filesystem Desktop Extension

This extension allows Claude to interact with your local filesystem, enabling it to read and write files directly. This can be useful for tasks such as file management, data processing, and automation of repetitive tasks. The extension provides a set of tools that can be used to navigate directories, read file contents, and write new files or modify existing ones.

Underneath the hood, it uses @modelcontextprotocol/server-filesystem v2026.7.4.

14 tools reported — Publisher-reported; not verified by Pod.

For agents

This page has a Markdown and a JSON twin. Pod is also queryable over MCP at https://api.askpod.ai/mcp/read.