Top 10 Developer & Coding MCP Servers for AI Agents (2026)

search_repositories(query)

Search for GitHub repositories with language, star, and owner qualifiers.

get_file_contents(owner, repo, path, ref?)

Fetch file or directory contents from a specified branch or commit.

create_pull_request(owner, repo, title, head, base, body?)

Create a new pull request across branches or forks.

list_workflow_runs(owner, repo, workflow_id?)

Retrieve recent GitHub Actions CI/CD workflow run statuses and failure logs.

Limitations

• Requires a GitHub Personal Access Token (PAT) with broad repository permissions.
• Large repo-wide code searches can return extensive JSON responses that consume significant context tokens.

resolve_library_id(libraryName)

Resolves a library package name into the canonical documentation index ID.

query_docs(libraryId, query)

Searches official documentation and extracts concise, relevant API snippets.

Limitations

• Requires outbound network connectivity to Upstash's documentation indexing service.
• Internal proprietary enterprise libraries must be indexed separately.

find_symbol(name, kind?)

Locate class, interface, or function declarations across the entire codebase.

find_references(symbol, file_path)

Find all call sites and usages of a specific code symbol.

get_ast_tree(file_path, max_depth?: number)

Returns a compressed syntactic hierarchy of a file to reduce token overhead.

Limitations

• Requires Python 3.10+ and a local Tree-sitter build environment.
• Large monorepos require initial indexing time before symbol queries become instantaneous.

execute_command(command, timeout_ms?: number)

Execute a shell command in the workspace with bounded timeout and exit code capture.

read_file(path, offset?: number, limit?: number)

Read file contents with line-based pagination to preserve context window tokens.

edit_file_diff(path, old_string, new_string)

Perform precise, targeted string replacement on local source files.

Limitations

• Has access to local system shell; requires careful workspace path scoping to prevent unintended changes.
• Long-running commands must be managed with explicit timeouts to avoid blocking agent turns.

list_tables(database?)

Enumerate database tables, views, and structural constraints.

describe_table(table_name)

Inspect column names, data types, primary keys, and foreign key relationships.

execute_query(query, params?: array)

Execute a parameterized SQL query with automatic row limit clamping.

Limitations

• Direct write queries must be restricted via database user permissions to prevent accidental data drops.
• Very wide tables with hundreds of columns should be queried with explicit column selectors.

get_issue(issue_id)

Retrieve comprehensive details, frequency, and stack trace for a specific Sentry issue.

list_recent_errors(project, query?)

Search active unhandled exceptions and performance anomalies in a project.

get_event_breadcrumbs(event_id)

Inspect chronological user interactions, network requests, and console logs leading to an exception.

Limitations

• Requires a Sentry User Auth Token with issue read permissions.
• Stack traces for minified code require sourcemaps already uploaded to Sentry.

list_workers(account_id)

List all deployed Cloudflare Workers scripts and their active routes.

query_d1_database(database_id, sql)

Execute SQL queries on edge-replicated Cloudflare D1 SQLite databases.

get_pages_deployment(project_name, deployment_id)

Inspect Cloudflare Pages build logs and deployment status.

Limitations

• Remote HTTP transport requires an MCP host with OAuth support (VS Code 1.101+, Cursor).
• Write operations require explicit Cloudflare API account token scoping.

list_pods(namespace?)

List running, pending, and crash-looping pods in a target namespace.

get_pod_logs(pod_name, namespace?, tail_lines?: number)

Fetch tail logs from specific pod containers to diagnose crash loops.

describe_resource(kind, name, namespace?)

Inspect Kubernetes events, resource limits, and status conditions.

Limitations

• Relies on active local `~/.kube/config` context; switching clusters changes agent scope.
• Mutating operations (apply/delete) should be gated with RBAC read-only service accounts.

search_providers(query)

Search official and community Terraform providers in the registry.

get_resource_schema(provider, resource_type)

Fetch required arguments, optional attributes, and types for any Terraform resource.

validate_module(module_path)

Verify syntax and provider constraints for a local Terraform configuration.

Limitations

• Focuses on provider schema and module validation; does not execute `terraform apply` directly.
• Requires Docker or Go toolchain for binary execution.

search_issues(query, teamId?, status?)

Search Linear issues by title, description, assignee, and state.

create_issue(title, teamId, description?, priority?: number)

Create a new issue with markdown description, priority level, and labels.

update_issue(id, stateId?, assigneeId?)

Update issue progress, assignee, or priority.

add_comment(issueId, body)

Post a status update or automated PR summary comment to a Linear ticket.

Limitations

• Requires a Linear Personal API Key with issue write access.
• Team IDs must be resolved once or cached in agent context.