feat(agent-harness): execute validated remote MCP tools - #5743
Closed
iscekic wants to merge 3 commits into
Closed
Conversation
This was referenced Aug 30, 2026
Contributor
Code Review SummaryStatus: No Issues Found | Recommendation: Merge Files Reviewed (2 files)
Reviewed by grok-4.6 · Input: 397.9K · Output: 29.6K · Cached: 559.1K Review guidance: REVIEW.md from base branch |
This was referenced Aug 30, 2026
This was referenced Aug 30, 2026
This was referenced Aug 31, 2026
Contributor
Author
|
Closing: the owner stopped this workflow section. The branch is retained. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No new behavior — the new remote tool checks are not active in the product.
Summary
executeMcpadds bounded Model Context Protocol (MCP) discovery and execution throughmcp.discover,mcp.call,McpConnection, andRunLimits, without activating the harness.The maintained
CfWorkerJsonSchemaValidatorvalidates a restricted schema vocabulary; invalid arguments block dispatch, and changedconfigurationVersionordefinitionVersionvalues require rediscovery.ToolOutcomereturns validated data or sanitized failures, preserves the first failure during cancellation, and reports post-dispatch failures asoutcome_unknownwithout replay.Files
services/agent-harness/src/tools/mcp.ts— Source; added, 199 lines (+199/-0). Exports the runtime and re-exportsMcpConnection; consumes ephemeral gateway authorization without copying it into discovery records or failures. UsesToolRequestSchemato accept only the two MCP requests. Checks both schemas, rejects malformed schemas, references, and unknown keywords, requires output schemas, and rejects tools that require task execution. Supports checked types, object and array rules, enums, constants, numeric and size bounds, and metadata. Paginates discovery, rejects repeated cursors, hashes canonical tool definitions withSHA-256, and returns an empty list when no connections exist. Calls rediscover the selected tool, compare both versions, validate arguments, and return only schema-checkedcontentandstructuredContent. A missing server or tool returns an unavailable failure. Shares one deadline and aggregate response budget across connections; separately limits input, discovery records, and result bytes, without timeout resets on progress. Closes clients and clears timers; classifies protocol, parsing, and software development kit (SDK) Zod Mini or Classic errors without provider diagnostics. Only pre-dispatch unavailability or reauthorization failures allow retry.services/agent-harness/src/tools/mcp.test.ts— Test; added, 198 lines (+198/-0). Confirms that Ask approval still applies despite read-only hints and trusted-read dispatch input. Covers successful discovery and calls, credential exclusion, schema and argument rejection, stale versions, and sanitized Hypertext Transfer Protocol (HTTP) failures. Exercises malformed or missing results, remote errors, lost or stalled responses, response and output limits, one-time effects, and empty discovery.Tests: 1 test file added,
mcp.test.ts, with 198 added lines and no deleted lines.Generated: 0 changed files.
Visual Changes
Visual Changes: N/A
Verification
No manual tests ran in this round because this level does not activate the harness.
Adapter doubles do not prove live provider behavior.
Reviewer Notes
Human steps: None before merge or after merge.
Kilo-Org/cloud. Worktree:/Users/igor/Projects/.worktrees/shared-agent-harness-3bb0.shared-agent-harness-3bb0-s25...shared-agent-harness-3bb0-s26.Runtime verification remains pending at the stack tip. This level adds validated MCP discovery and execution without activating the harness.
Stacked PRs — merge bottom to top. Each level shows only its own diff.
Runtime verification (E2E, user advocacy, simplify) runs on the tip PR over every level.
Every level keeps its own checks, its own bot review, and its own threads; each one is answered on its own PR.
Each level is its own deliverable: it builds and passes its own checks alone.
A finding on a level is repaired on that level, then carried upward with stack.sh forward.
shared-agent-harness-3bb0— chore(agent-harness): register workspaces and enforce CI boundaries #5632shared-agent-harness-3bb0-s2— feat(agent-harness): define portable domain and snapshots #5637shared-agent-harness-3bb0-s3— feat(agent-harness): define commands tools and permission policy #5639shared-agent-harness-3bb0-s4— feat(agent-harness): share client state and cursor recovery #5643shared-agent-harness-3bb0-s5— feat(agent-harness): persist command intents and execution receipts #5647shared-agent-harness-3bb0-s6— feat(db): add harness ingress grants and retirement fences #5655shared-agent-harness-3bb0-s7— feat(agent-harness): deliver legacy history and project durable text #5659shared-agent-harness-3bb0-s8— feat(agent-harness): authorize durable grants and registered clients #5662shared-agent-harness-3bb0-s9— feat(agent-harness): fence retirement and retry payload cleanup #5667shared-agent-harness-3bb0-s10— feat(agent-harness): persist authoritative state in SQLite #5675shared-agent-harness-3bb0-s11— feat(agent-harness): admit durable runs and revisioned commands #5678shared-agent-harness-3bb0-s12— feat(agent-harness): recover queued runs and stream checkpointed steps #5688shared-agent-harness-3bb0-s13— feat(agent-harness): resolve interactions and dispatch tools sequentially #5693shared-agent-harness-3bb0-s14— feat(agent-harness): fence designated client tool execution #5697shared-agent-harness-3bb0-s15— feat(agent-harness): synchronize durable snapshots and legacy history #5701shared-agent-harness-3bb0-s16— feat(agent-harness): reuse authorized invitations with durable replay #5704shared-agent-harness-3bb0-s17— feat(integrations): bound repository transport for harness reads #5710shared-agent-harness-3bb0-s18— feat(integrations): expose bounded authorized repository reads #5714shared-agent-harness-3bb0-s19— feat(agent-harness): expose named authorized resource reads #5718shared-agent-harness-3bb0-s20— feat(sessions): bound history transport for harness reads #5724shared-agent-harness-3bb0-s21— feat(agent-harness): read scoped Cloud Agent context and progress #5726shared-agent-harness-3bb0-s22— fix(agent-harness): preserve ordered Cloud Agent dispatch identity #5731shared-agent-harness-3bb0-s23— feat(agent-harness): hand coding work to authorized Cloud Agent sessions #5733shared-agent-harness-3bb0-s24— feat(agent-harness): authorize scoped MCP gateway connections #5737shared-agent-harness-3bb0-s25— feat(agent-harness): bound MCP gateway transport in the Worker #5740shared-agent-harness-3bb0-s26— feat(agent-harness): execute validated remote MCP tools #5743 ← this PRshared-agent-harness-3bb0-s27— refactor(exa): share provider dispatch and usage recording #5746shared-agent-harness-3bb0-s28— feat(agent-harness): authorize bounded web provider requests #5747shared-agent-harness-3bb0-s29— feat(agent-harness): normalize web sources and preserve citations #5749shared-agent-harness-3bb0-s30— feat(agent-harness): define closed internal operation contracts #5753shared-agent-harness-3bb0-s31— feat(agent-harness): authorize internal maintenance operations #5754shared-agent-harness-3bb0-s32— feat(agent-harness): authorize named Kilo operation dispatch #5755shared-agent-harness-3bb0-s33— feat(agent-harness): authorize internal provider operations #5757shared-agent-harness-3bb0-s34— feat(agent-harness): secure the internal operations endpoint #5758shared-agent-harness-3bb0-s35— feat(agent-harness): bound and sanitize model streams #5767shared-agent-harness-3bb0-s36— feat(agent-harness): secure billed model inference #5776shared-agent-harness-3bb0-s37— test(agent-harness): cover model gateway security boundaries #5777 (tip)